© 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. 10-RES_POST_32K-OAI
    11. 31642
    Prev
    Next
    INDEX
    Explanations

    words related to visual perception and appearance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    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
    55
    +0.10
    0.4%
    4
    +0.09
    0.4%
    352
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    603
    +0.10
    0.07
    55
    +0.09
    0.06
    200
    +0.09
    0.05
    Negative Logits
     Recomm
    -0.76
     Repeat
    -0.70
    UA
    -0.67
    trl
    -0.67
    rosso
    -0.67
    isSpecialOrderable
    -0.66
    ãĥĩãĤ£
    -0.66
     Dupl
    -0.63
    aceae
    -0.62
     MMR
    -0.61
    POSITIVE LOGITS
     forward
    1.00
     delighted
    0.89
     thrilled
    0.88
     pleased
    0.85
     proud
    0.83
     remarkably
    0.79
     nostalg
    0.78
     radiant
    0.78
     strikingly
    0.77
     destined
    0.76
    Activations Density 0.304%

    No Known Activations