© 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. 8498
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations or entities associated with the word "Barb" and various forms of the word "tub."

    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
    314
    +0.14
    0.6%
    240
    +0.12
    0.6%
    370
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    211
    +0.14
    0.01
    326
    +0.12
    0.02
    288
    +0.10
    0.02
    Negative Logits
     lig
    -0.68
     celeb
    -0.65
     Chronicle
    -0.62
     Strikes
    -0.61
     psy
    -0.61
     Wilhelm
    -0.59
     Wildcats
    -0.59
     Brock
    -0.59
     censor
    -0.58
     lockout
    -0.57
    POSITIVE LOGITS
    ular
    1.36
    oons
    1.13
    ularity
    1.10
    glers
    1.07
    unda
    1.02
    ozo
    1.01
    oon
    0.98
    rosse
    0.97
    ulations
    0.97
    ambo
    0.96
    Activations Density 0.052%

    No Known Activations