© 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. 5482
    Prev
    Next
    INDEX
    Explanations

    references to violence and harm, particularly involving murder and assault

    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
    350
    +0.09
    0.4%
    464
    +0.09
    0.4%
    553
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    686
    +0.09
    0.04
    507
    +0.09
    0.06
    486
    +0.09
    0.05
    Negative Logits
    fare
    -0.84
    wcs
    -0.80
    inctions
    -0.79
    estone
    -0.75
    issues
    -0.74
    edition
    -0.73
    aston
    -0.72
    ixtape
    -0.70
    interstitial
    -0.70
    inction
    -0.69
    POSITIVE LOGITS
     somebody
    1.38
     someone
    1.36
     anybody
    1.22
     anyone
    1.14
    someone
    1.12
     him
    1.06
     whoever
    1.01
     strangers
    0.99
     others
    0.99
     fellow
    0.95
    Activations Density 0.482%

    No Known Activations