© 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. 8194
    Prev
    Next
    INDEX
    Explanations

    the first-person pronoun "I" and its variations, indicating a focus on personal experiences or expressions

    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
    38
    +0.11
    0.5%
    302
    +0.10
    0.5%
    572
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    354
    +0.11
    0.11
    566
    +0.10
    0.10
    502
    +0.10
    0.10
    Negative Logits
     gearing
    -0.65
    Ħ¢
    -0.63
     helicop
    -0.63
    Temp
    -0.61
    endi
    -0.61
     outings
    -0.58
     bott
    -0.57
    acly
    -0.57
    anta
    -0.56
     shifts
    -0.54
    POSITIVE LOGITS
    cknow
    0.92
    ne
    0.76
    bid
    0.73
    nex
    0.72
    igate
    0.69
     disapprove
    0.69
    semble
    0.69
    pse
    0.68
    abba
    0.67
    BLE
    0.66
    Activations Density 0.424%

    No Known Activations