© 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. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 4957
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Holy."

    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
    459
    +0.15
    0.7%
    420
    +0.12
    0.6%
    288
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    345
    +0.15
    0.01
    48
    +0.12
    0.01
    420
    +0.10
    0.01
    Negative Logits
    PsyNetMessage
    -0.72
    icult
    -0.71
    ilant
    -0.68
    phrine
    -0.66
    izen
    -0.66
     inhibitors
    -0.66
    idian
    -0.64
    abin
    -0.64
    Downloadha
    -0.63
    oidal
    -0.61
    POSITIVE LOGITS
     Grail
    1.04
     Trinity
    0.79
     gra
    0.73
    father
    0.70
    rament
    0.69
    lehem
    0.68
    orical
    0.65
    oslav
    0.65
     smokes
    0.64
    CHR
    0.64
    Activations Density 0.026%

    No Known Activations