© 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. 10-RES_POST_32K-OAI
    11. 30381
    Prev
    Next
    INDEX
    Explanations

    prepositions indicating time or location

    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
    509
    +0.13
    0.6%
    314
    +0.10
    0.4%
    195
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    725
    +0.13
    0.04
    616
    +0.10
    0.04
    611
    +0.09
    0.04
    Negative Logits
     dstg
    -0.63
     vulner
    -0.61
     mathemat
    -0.60
     (-
    -0.58
     predic
    -0.57
     constitu
    -0.57
     concess
    -0.56
     âĢ¦"
    -0.56
     offensively
    -0.56
    .–
    -0.56
    POSITIVE LOGITS
    neath
    1.36
    ward
    1.14
    forming
    0.99
    gest
    0.95
    cest
    0.92
    visible
    0.90
    formed
    0.89
    sofar
    0.88
    come
    0.87
    juries
    0.86
    Activations Density 0.233%

    No Known Activations