© 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. 5445
    Prev
    Next
    INDEX
    Explanations

    phrases related to the outcomes of events or situations

    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
    288
    +0.25
    0.9%
    195
    +0.19
    0.7%
    718
    +0.17
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.25
    0.13
    724
    +0.19
    0.09
    540
    +0.17
    0.09
    Negative Logits
    aps
    -1.12
    ondo
    -1.05
    ker
    -1.04
    agna
    -0.95
    arij
    -0.94
    ordes
    -0.94
    yi
    -0.94
    sis
    -0.94
    king
    -0.93
    lems
    -0.91
    POSITIVE LOGITS
    bringer
    1.13
     outcome
    1.13
     outcomes
    1.05
     thereof
    1.02
     Yanuk
    1.01
    romeda
    0.94
    ality
    0.86
    fulness
    0.86
    200000
    0.81
     unfold
    0.79
    Activations Density 1.611%

    No Known Activations