© 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. 6702
    Prev
    Next
    INDEX
    Explanations

    instances of letters or syllables that repeat in various forms

    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
    218
    +0.14
    0.7%
    527
    +0.11
    0.5%
    284
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.14
    0.03
    130
    +0.11
    0.02
    232
    +0.11
    0.03
    Negative Logits
    esthetic
    -0.86
    esthesia
    -0.79
    EMENT
    -0.78
    iments
    -0.76
    ENC
    -0.75
    igators
    -0.73
    iment
    -0.73
    arov
    -0.69
    iam
    -0.68
    audi
    -0.68
    POSITIVE LOGITS
    crow
    0.94
    nces
    0.82
    aneers
    0.76
     Crus
    0.75
    stal
    0.68
    ycle
    0.68
    Ø©
    0.68
    wart
    0.68
     crus
    0.66
    atism
    0.65
    Activations Density 0.162%

    No Known Activations