© 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. 7311
    Prev
    Next
    INDEX
    Explanations

    references to notable individuals and their achievements

    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
    244
    +0.13
    0.6%
    314
    +0.11
    0.5%
    547
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.13
    0.17
    224
    +0.11
    0.14
    430
    +0.11
    0.18
    Negative Logits
     Saiyan
    -0.69
    ikarp
    -0.64
     issu
    -0.63
     FY
    -0.59
     NON
    -0.58
     =================
    -0.56
    minist
    -0.56
     IPM
    -0.56
     experien
    -0.55
    These
    -0.55
    POSITIVE LOGITS
     him
    0.93
     whom
    0.76
     teammate
    0.74
    his
    0.73
    aus
    0.71
     classmate
    0.71
    him
    0.71
    kson
    0.65
    else
    0.65
     he
    0.64
    Activations Density 3.819%

    No Known Activations