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. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 8-RES_POST_32K-OAI
    6. 5243
    Prev
    Next
    INDEX
    Explanations

    terms related to attribution or causation

    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
    569
    +0.10
    0.5%
    711
    +0.10
    0.4%
    698
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    541
    +0.10
    0.03
    665
    +0.10
    0.03
    569
    +0.09
    0.02
    Negative Logits
    lite
    -0.90
    rawdownloadcloneembedreportprint
    -0.79
    steel
    -0.71
    enegger
    -0.66
    rentice
    -0.60
    mpeg
    -0.59
    oto
    -0.58
     acad
    -0.57
    nea
    -0.57
    undown
    -0.57
    POSITIVE LOGITS
     blame
    1.23
     responsibility
    0.84
     importance
    0.79
     motives
    0.73
     undue
    0.72
     origin
    0.70
    credit
    0.69
    phas
    0.69
     similarities
    0.67
     attribut
    0.67
    Activations Density 0.160%

    No Known Activations