© 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. 6894
    Prev
    Next
    INDEX
    Explanations

    code snippets and commands related to programming languages

    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
    604
    +0.17
    0.6%
    488
    +0.16
    0.5%
    68
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.17
    0.05
    605
    +0.16
    0.04
    220
    +0.15
    0.04
    Negative Logits
    THIS
    -1.11
     nomine
    -1.08
    âĸ¬
    -1.05
    Tracker
    -1.03
    Ü
    -1.02
     Mutual
    -1.00
     behavi
    -0.99
     contrace
    -0.99
     Schwarz
    -0.98
    HCR
    -0.97
    POSITIVE LOGITS
    0
    1.46
    9
    1.39
    cc
    1.36
    916
    1.33
    7
    1.33
    8
    1.33
    cd
    1.32
    616
    1.30
    6
    1.28
    864
    1.27
    Activations Density 0.450%

    No Known Activations