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. 3958
    Prev
    Next
    INDEX
    Explanations

    phrases related to societal issues or observations on human behavior

    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
    735
    +0.08
    0.5%
    483
    +0.08
    0.5%
    128
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    237
    +0.08
    0.04
    534
    +0.08
    0.04
    230
    +0.08
    0.04
    Negative Logits
    potion
    -0.64
    idav
    -0.64
     Cinderella
    -0.62
    vez
    -0.60
    illac
    -0.59
    PsyNetMessage
    -0.56
    inth
    -0.55
    pb
    -0.53
     Guan
    -0.53
    chard
    -0.53
    POSITIVE LOGITS
     sorts
    0.83
     kinds
    0.62
     ages
    0.61
     proportions
    0.56
     parties
    0.55
     manners
    0.55
     committees
    0.54
    ocating
    0.54
    aughtered
    0.51
     disciplines
    0.51
    Activations Density 0.272%

    No Known Activations