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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14154
    Prev
    Next
    INDEX
    Explanations

    mathematical formulae

    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
    578
    +0.15
    0.5%
    482
    +0.15
    0.5%
    343
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.15
    0.07
    482
    +0.15
    0.06
    104
    +0.14
    0.05
    Negative Logits
    swick
    -0.97
    icol
    -0.96
    icone
    -0.91
    âĹ¼
    -0.91
    ophob
    -0.88
    ript
    -0.87
    sed
    -0.86
     Hort
    -0.86
    xual
    -0.86
    vent
    -0.85
    POSITIVE LOGITS
    Thirty
    1.65
    âĺħ
    1.02
    010
    1.01
     ILCS
    1.01
    ŃĶ
    1.00
    678
    0.99
    th
    0.99
    anging
    0.98
    teen
    0.97
     minutes
    0.95
    Activations Density 1.575%

    No Known Activations