© 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
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 4646
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, especially dashes and hyphens

    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
    329
    +0.14
    0.6%
    202
    +0.12
    0.5%
    494
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    720
    +0.14
    0.09
    546
    +0.12
    0.06
    160
    +0.11
    0.07
    Negative Logits
     Entered
    -0.63
    ribe
    -0.61
     Born
    -0.60
     Firstly
    -0.60
     Hood
    -0.57
    ICO
    -0.56
    ICA
    -0.55
    senal
    -0.55
     Remastered
    -0.55
     Bought
    -0.55
    POSITIVE LOGITS
    without
    0.94
    even
    0.93
    whatever
    0.84
     regardless
    0.84
    literally
    0.83
    provided
    0.82
    unless
    0.81
     thereby
    0.81
    instead
    0.80
    excluding
    0.79
    Activations Density 0.354%

    No Known Activations