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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4232
    Prev
    Next
    INDEX
    Explanations

    occurrences of underscores and other non-alphabetic characters

    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
    373
    +0.21
    1.0%
    176
    +0.12
    0.5%
    382
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    160
    +0.21
    0.05
    107
    +0.12
    0.04
    229
    +0.10
    0.03
    Negative Logits
     contestant
    -0.70
     Ninth
    -0.70
     Grimm
    -0.69
     Columb
    -0.65
     descending
    -0.64
     oneself
    -0.63
     Fifth
    -0.62
     Pau
    -0.62
     Rats
    -0.62
     Humans
    -0.62
    POSITIVE LOGITS
    disable
    1.09
    cfg
    0.96
    enable
    0.93
    flush
    0.93
    file
    0.92
    gpu
    0.92
    Enable
    0.92
    cli
    0.85
    install
    0.83
    ctl
    0.83
    Activations Density 0.140%

    No Known Activations