© 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. 29177
    Prev
    Next
    INDEX
    Explanations

    key identifiers, particularly names or references to specific individuals or groups

    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
    599
    +0.10
    0.4%
    31
    +0.09
    0.4%
    321
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    351
    +0.10
    0.02
    231
    +0.09
    0.02
    371
    +0.09
    0.02
    Negative Logits
    phe
    -0.76
     MMO
    -0.71
     Zoe
    -0.70
     Pv
    -0.69
     Tul
    -0.69
    onia
    -0.69
    atively
    -0.68
    eus
    -0.68
    oine
    -0.67
    pie
    -0.67
    POSITIVE LOGITS
    éŃĶ
    0.80
    Red
    0.80
    Conn
    0.78
    Rel
    0.77
    English
    0.75
    Inv
    0.74
    Eng
    0.74
    ynam
    0.73
    Energy
    0.73
    quin
    0.71
    Activations Density 0.097%

    No Known Activations