© 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. 27575
    Prev
    Next
    INDEX
    Explanations

    identifiers and references related to entities, such as people or organizations

    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
    497
    +0.12
    0.5%
    584
    +0.11
    0.5%
    651
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    103
    +0.12
    0.02
    127
    +0.11
    0.01
    584
    +0.09
    0.02
    Negative Logits
    baugh
    -0.76
    theless
    -0.71
     FANTASY
    -0.69
     guiName
    -0.68
    ham
    -0.67
    conom
    -0.65
    Laughs
    -0.64
    uca
    -0.64
    laughs
    -0.63
    flies
    -0.62
    POSITIVE LOGITS
    ternity
    0.86
    ħĭ
    0.81
    entity
    0.78
    ¶æ
    0.66
    peror
    0.65
    ĻĤ
    0.64
    atically
    0.64
    ³
    0.63
    teness
    0.63
    eteen
    0.62
    Activations Density 0.130%

    No Known Activations