© 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. 8605
    Prev
    Next
    INDEX
    Explanations

    instances of the word "fresh."

    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
    459
    +0.13
    0.6%
    201
    +0.10
    0.5%
    217
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    339
    +0.13
    0.02
    660
    +0.10
    0.02
    201
    +0.10
    0.02
    Negative Logits
    fman
    -0.61
    eering
    -0.61
     mund
    -0.60
    oried
    -0.60
    rael
    -0.57
     Loren
    -0.56
     respecting
    -0.56
    err
    -0.55
    ormal
    -0.55
    oppable
    -0.54
    POSITIVE LOGITS
    ness
    1.21
    waters
    0.93
    water
    0.88
    faced
    0.82
    lins
    0.82
    lings
    0.81
    liness
    0.79
    lish
    0.79
    meat
    0.78
    bread
    0.72
    Activations Density 0.075%

    No Known Activations