© 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. 5034
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "wid" which appears to relate to widgets or some form of content placeholder

    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
    373
    +0.10
    0.5%
    195
    +0.10
    0.5%
    13
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.10
    0.01
    195
    +0.10
    0.01
    211
    +0.10
    0.01
    Negative Logits
     Hebdo
    -0.68
     Kafka
    -0.68
     Singer
    -0.67
     Felix
    -0.67
     surg
    -0.64
    paio
    -0.63
     Shepherd
    -0.63
     Bunker
    -0.62
     riot
    -0.60
     Morse
    -0.59
    POSITIVE LOGITS
    gets
    0.96
    aho
    0.92
    wid
    0.85
    lied
    0.77
    uously
    0.75
    itized
    0.75
    ¥
    0.72
    ><
    0.72
    emption
    0.71
    ewater
    0.70
    Activations Density 0.012%

    No Known Activations