© 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. 5156
    Prev
    Next
    INDEX
    Explanations

    references to the term "SF" and its related contexts

    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
    330
    +0.11
    0.5%
    242
    +0.10
    0.4%
    269
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.11
    0.01
    659
    +0.10
    0.01
    323
    +0.09
    0.01
    Negative Logits
    lain
    -0.83
    stall
    -0.76
    taker
    -0.70
    pin
    -0.68
    pins
    -0.68
    ividual
    -0.66
    eering
    -0.65
     Lyme
    -0.64
    xual
    -0.64
    lly
    -0.63
    POSITIVE LOGITS
     Chronicle
    0.86
    WA
    0.83
    conservancy
    0.82
    ORTS
    0.77
    SF
    0.75
    GH
    0.74
    PD
    0.73
    ifty
    0.72
    IF
    0.72
    antasy
    0.70
    Activations Density 0.038%

    No Known Activations