© 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. 8-RES_POST_32K-OAI
    11. 8623
    Prev
    Next
    INDEX
    Explanations

    dates or references to specific days in the format of "Nov [date]"

    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
    163
    +0.15
    0.7%
    288
    +0.10
    0.5%
    223
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    223
    +0.15
    0.03
    631
    +0.10
    0.02
    188
    +0.09
    0.02
    Negative Logits
    jriwal
    -0.87
    cher
    -0.79
    76561
    -0.75
    pires
    -0.75
    PLA
    -0.74
    gypt
    -0.74
    lement
    -0.74
    gotten
    -0.73
    ensing
    -0.73
    ptin
    -0.72
    POSITIVE LOGITS
    ality
    0.68
    е
    0.68
    isms
    0.67
    а
    0.67
    ãĥĥãĥĪ
    0.66
    etta
    0.66
    о
    0.64
     Normandy
    0.64
    aldi
    0.63
    olics
    0.63
    Activations Density 0.039%

    No Known Activations