© 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. 7210
    Prev
    Next
    INDEX
    Explanations

    sequences of numerical and alphanumeric patterns

    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
    711
    +0.15
    0.7%
    471
    +0.13
    0.6%
    373
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.15
    -0.05
    107
    +0.13
    0.08
    23
    +0.11
    0.08
    Negative Logits
     Tik
    -0.77
     Synd
    -0.77
     anth
    -0.76
    anth
    -0.75
     Nest
    -0.74
    xt
    -0.71
     Masquerade
    -0.71
    imen
    -0.69
     welf
    -0.68
    Sy
    -0.67
    POSITIVE LOGITS
    June
    0.92
    06
    0.89
     06
    0.88
    6
    0.82
    Jun
    0.81
    2006
    0.81
    266
    0.80
    boa
    0.80
    é¾įå¥ij士
    0.78
     Kemp
    0.77
    Activations Density 1.884%

    No Known Activations