© 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. 3763
    Prev
    Next
    INDEX
    Explanations

    references to benefits or advantages in various contexts

    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
    393
    +0.29
    1.0%
    608
    +0.20
    0.7%
    669
    +0.19
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.29
    0.10
    669
    +0.20
    0.08
    362
    +0.19
    0.07
    Negative Logits
    soDeliveryDate
    -1.22
    earchers
    -1.06
    heading
    -1.04
    grass
    -1.00
    selves
    -0.99
    hens
    -0.99
    iron
    -0.95
    soType
    -0.94
    runner
    -0.94
    nih
    -0.94
    POSITIVE LOGITS
     various
    1.03
     domestic
    0.99
     such
    0.98
     heightened
    0.95
     any
    0.95
     treatment
    0.94
     occasional
    0.93
    ãĥīãĥ©ãĤ´ãĥ³
    0.93
     unequ
    0.92
     differing
    0.92
    Activations Density 1.016%

    No Known Activations