© 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. 4787
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly periods

    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
    413
    +0.11
    0.5%
    11
    +0.10
    0.5%
    77
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    148
    +0.11
    0.01
    103
    +0.10
    0.01
    413
    +0.10
    0.01
    Negative Logits
     printers
    -0.73
    igham
    -0.65
     digitally
    -0.64
     ethic
    -0.64
    ervatives
    -0.64
     presses
    -0.63
     holiest
    -0.63
     keyboards
    -0.63
     conclud
    -0.62
     backers
    -0.61
    POSITIVE LOGITS
    ©¶æ¥µ
    0.94
    ĨĴ
    0.86
    SHIP
    0.83
    auri
    0.81
    nant
    0.80
    section
    0.80
    SourceFile
    0.77
    ISTORY
    0.76
    wav
    0.74
    pmwiki
    0.72
    Activations Density 0.069%

    No Known Activations