© 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. 27224
    Prev
    Next
    INDEX
    Explanations

    references to numerical ranges or scales

    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
    224
    +0.12
    0.5%
    137
    +0.11
    0.5%
    290
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    435
    +0.12
    0.02
    99
    +0.11
    0.02
    575
    +0.11
    0.03
    Negative Logits
    rics
    -0.79
    roma
    -0.72
    chard
    -0.65
    SourceFile
    -0.62
     Bonds
    -0.62
    ··
    -0.62
     pulp
    -0.62
    äºĶ
    -0.61
    liga
    -0.60
    WN
    -0.60
    POSITIVE LOGITS
    finder
    1.50
     Rover
    1.15
    finding
    0.91
    find
    0.81
    seeing
    0.80
    ranging
    0.77
    ahead
    0.72
    ollah
    0.69
     anxiety
    0.69
    omorph
    0.67
    Activations Density 0.170%

    No Known Activations