© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 7093
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "evidence" and related terms indicating conditional or hypothetical statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    126
    +0.12
    0.6%
    369
    +0.10
    0.4%
    106
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    53
    +0.12
    0.02
    675
    +0.10
    0.02
    126
    +0.09
    0.02
    Negative Logits
    ĸļ
    -0.85
    ascript
    -0.83
    issance
    -0.69
    apest
    -0.67
     Medina
    -0.67
    lain
    -0.66
    spection
    -0.64
    ullivan
    -0.63
     Gibraltar
    -0.62
    illin
    -0.61
    POSITIVE LOGITS
    omaly
    0.87
    Known
    0.81
    vari
    0.80
     Marketable
    0.74
     sqor
    0.74
    styles
    0.73
    soType
    0.70
     Influ
    0.68
     Surviv
    0.68
     Variant
    0.67
    Activations Density 0.084%

    No Known Activations