© 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. 4947
    Prev
    Next
    INDEX
    Explanations

    words or phrases indicating necessity or requirements

    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
    525
    +0.15
    0.7%
    468
    +0.13
    0.6%
    50
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    179
    +0.15
    0.01
    209
    +0.13
    0.01
    148
    +0.12
    0.01
    Negative Logits
     Painter
    -0.78
     Pain
    -0.73
     Lei
    -0.69
     Dusk
    -0.67
     Nose
    -0.66
     Feather
    -0.66
     Clair
    -0.66
     Flame
    -0.65
     Hazard
    -0.65
     Stout
    -0.64
    POSITIVE LOGITS
    intendo
    0.79
    cation
    0.74
    ranch
    0.73
    geoning
    0.71
    mob
    0.71
    yssey
    0.71
    puting
    0.71
    mson
    0.70
    rats
    0.70
    yout
    0.70
    Activations Density 0.041%

    No Known Activations