Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 3959
    Prev
    Next
    INDEX
    Explanations

    texts related to government resolutions and agreements

    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
    640
    +0.48
    1.6%
    18
    +0.14
    0.5%
    726
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.48
    0.17
    94
    +0.14
    0.09
    160
    +0.13
    0.09
    Negative Logits
    hement
    -1.21
    atis
    -1.06
    sburgh
    -1.05
     Thornton
    -1.01
     steroids
    -1.01
     neighb
    -0.96
     psychiat
    -0.95
    aday
    -0.92
     emancipation
    -0.92
    rity
    -0.91
    POSITIVE LOGITS
    ³³³³³³³³
    1.24
    ³³³³
    1.19
    ³³³³³³³³³³³³³³³³
    1.17
    âĹı
    1.12
    ;;;;
    1.11
    LAB
    1.09
    "â̦
    1.08
    ³³³
    1.07
    QB
    1.07
    Beta
    1.06
    Activations Density 1.597%

    No Known Activations