© 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 EvalsExportsAPI 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. 6713
    Prev
    Next
    INDEX
    Explanations

    words indicating demonstration or evidence of skill, capability, or performance

    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
    135
    +0.11
    0.5%
    30
    +0.10
    0.5%
    342
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    483
    +0.11
    0.04
    274
    +0.10
    0.04
    724
    +0.09
    0.05
    Negative Logits
     racket
    -0.70
     Madness
    -0.68
    lift
    -0.66
     affairs
    -0.63
     copyrighted
    -0.60
    Summary
    -0.60
     FIG
    -0.60
     cigarette
    -0.58
     Sins
    -0.56
    abilia
    -0.56
    POSITIVE LOGITS
     knack
    0.76
     adept
    0.74
     patience
    0.73
     willingness
    0.73
     promise
    0.68
    senal
    0.66
    manuel
    0.65
    redo
    0.64
    ãĥ¼ãĥĨ
    0.64
    vd
    0.64
    Activations Density 0.434%

    No Known Activations