© 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. 8-RES_POST_32K-OAI
    11. 6748
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of "redemption."

    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
    199
    +0.12
    0.5%
    330
    +0.10
    0.5%
    373
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.12
    0.02
    365
    +0.10
    0.01
    534
    +0.09
    0.01
    Negative Logits
    Champ
    -0.74
    vernment
    -0.69
    emetery
    -0.68
     Frames
    -0.65
    rontal
    -0.65
     Developers
    -0.65
     Decoder
    -0.64
     Curve
    -0.64
     Console
    -0.62
    erella
    -0.61
    POSITIVE LOGITS
    season
    0.70
    jpg
    0.64
    hs
    0.64
    upt
    0.63
    theme
    0.62
    yd
    0.62
     gri
    0.62
    seeing
    0.61
    ston
    0.61
    je
    0.61
    Activations Density 0.090%

    No Known Activations