© 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. 30127
    Prev
    Next
    INDEX
    Explanations

    aspects related to technical specifications and dimensions in a descriptive context

    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
    373
    +0.13
    0.6%
    643
    +0.09
    0.4%
    258
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.13
    -0.03
    314
    +0.09
    -0.01
    284
    +0.09
    0.01
    Negative Logits
    igslist
    -0.80
    emale
    -0.77
    untled
    -0.73
    othal
    -0.68
    acus
    -0.66
    ruce
    -0.66
    issan
    -0.65
    bane
    -0.65
    ocry
    -0.65
    ĪĴ
    -0.63
    POSITIVE LOGITS
    ":"/
    0.82
     Sturgeon
    0.75
     EPA
    0.72
    ":["
    0.70
    Duration
    0.70
    "},"
    0.70
    Getty
    0.69
    Parameter
    0.68
     Getty
    0.64
    EPA
    0.62
    Activations Density 0.203%

    No Known Activations