© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 13076
    Prev
    Next
    INDEX
    Explanations

    structured text with a mix of technical and instructional content, possibly related to software development, medical equipment, and strategic gaming

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    393
    +0.28
    1.0%
    595
    +0.21
    0.7%
    669
    +0.17
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    595
    +0.28
    0.06
    669
    +0.21
    0.05
    643
    +0.17
    0.04
    Negative Logits
    Aren
    -1.11
    Origin
    -1.00
    isf
    -0.98
    eneg
    -0.98
    Bound
    -0.96
    ãĤ´
    -0.96
    Nap
    -0.96
    Grab
    -0.95
    Corn
    -0.94
     corrid
    -0.93
    POSITIVE LOGITS
     necessarily
    1.28
     relying
    1.26
     simply
    1.12
     outright
    1.11
     letting
    1.11
     bothering
    1.08
     having
    1.06
     anything
    1.06
     worrying
    1.04
     allowing
    1.04
    Activations Density 0.677%

    No Known Activations