© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 8-RES_POST_32K-OAI
    6. 4835
    Prev
    Next
    INDEX
    Explanations

    references to "others" or the concept of other people

    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
    393
    +0.10
    0.5%
    387
    +0.10
    0.5%
    762
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    224
    +0.10
    0.02
    762
    +0.10
    0.03
    225
    +0.09
    0.02
    Negative Logits
     Ulster
    -0.68
     Hulk
    -0.66
     Doc
    -0.65
    veyard
    -0.62
     Playoffs
    -0.61
     Mecca
    -0.61
     Patriarch
    -0.60
     Shack
    -0.59
    Accessory
    -0.59
     Mongolia
    -0.59
    POSITIVE LOGITS
    worldly
    1.10
    paces
    0.89
    cius
    0.85
     besides
    0.81
    cript
    0.81
    ourcing
    0.80
    clerosis
    0.78
     who
    0.77
     fortunate
    0.74
     contributing
    0.74
    Activations Density 0.051%

    No Known Activations