© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 7258
    Prev
    Next
    INDEX
    Explanations

    references to types of explosives or incendiary devices

    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
    459
    +0.14
    0.7%
    71
    +0.10
    0.4%
    247
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.14
    0.08
    373
    +0.10
    -0.04
    659
    +0.09
    0.07
    Negative Logits
    ©¶æ
    -0.83
    areth
    -0.82
    abouts
    -0.67
     resemb
    -0.67
    ħĭ
    -0.66
    20439
    -0.61
     brackets
    -0.61
    icles
    -0.60
     fate
    -0.58
    tale
    -0.58
    POSITIVE LOGITS
    acker
    0.70
     raging
    0.68
    acks
    0.64
     Bullets
    0.61
     stoked
    0.59
    ulse
    0.58
    uously
    0.58
    aker
    0.57
    ackers
    0.56
    ovic
    0.56
    Activations Density 0.646%

    No Known Activations