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. 3906
    Prev
    Next
    INDEX
    Explanations

    phrases related to influence or influential entities

    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
    273
    +0.05
    0.5%
    231
    +0.05
    0.5%
    759
    +0.05
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.05
    0.08
    311
    +0.05
    0.02
    555
    +0.05
    0.05
    Negative Logits
     Dare
    -0.36
     Valiant
    -0.35
     Maiden
    -0.33
    lands
    -0.33
    plane
    -0.32
    gil
    -0.32
     Owl
    -0.32
    DAY
    -0.31
    thia
    -0.31
    pool
    -0.31
    POSITIVE LOGITS
    encer
    0.55
    encing
    0.51
    encers
    0.49
    ential
    0.48
    enced
    0.47
    enza
    0.44
    ences
    0.43
    ggles
    0.41
    enz
    0.40
    encia
    0.40
    Activations Density 0.560%

    No Known Activations