© 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 EvalsExportsinterp-engineNEWAPI 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. 11309
    Prev
    Next
    INDEX
    Explanations

    C++ code snippets, including printf statements and code examples with error handling

    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
    160
    +0.20
    0.7%
    553
    +0.16
    0.5%
    23
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.20
    0.06
    167
    +0.16
    0.01
    288
    +0.15
    0.07
    Negative Logits
    osponsors
    -1.19
    esville
    -1.08
    daq
    -1.08
     helicop
    -1.04
    gur
    -1.01
    won
    -0.97
    orus
    -0.97
     explan
    -0.96
    rha
    -0.96
    igne
    -0.95
    POSITIVE LOGITS
     cout
    1.15
    ++
    1.10
     std
    1.07
    imentary
    1.04
    ãĥĥãĥī
    1.01
     whistle
    1.01
     scratch
    1.01
    std
    0.96
     STL
    0.96
     deduction
    0.95
    Activations Density 1.055%

    No Known Activations