© 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. 7088
    Prev
    Next
    INDEX
    Explanations

    comparison operators in code

    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
    160
    +0.12
    0.5%
    107
    +0.11
    0.5%
    627
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    158
    +0.12
    0.05
    160
    +0.11
    0.05
    231
    +0.11
    0.04
    Negative Logits
     Peace
    -0.67
     pause
    -0.66
     outdoors
    -0.66
     omn
    -0.64
     weights
    -0.64
     interpol
    -0.64
     Ital
    -0.63
     slack
    -0.63
     scattering
    -0.63
     sign
    -0.63
    POSITIVE LOGITS
    unsigned
    1.06
    sup
    1.02
    br
    0.97
    tm
    0.97
    clinton
    0.95
    âĢ¦]
    0.95
    chrome
    0.93
    req
    0.92
    lower
    0.91
    sy
    0.91
    Activations Density 0.154%

    No Known Activations