© 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. 10-RES_POST_32K-OAI
    11. 31568
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "never" and its variations, indicating experiences that were absent or missing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    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
    756
    +0.12
    0.5%
    90
    +0.11
    0.5%
    307
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    551
    +0.12
    0.05
    139
    +0.11
    0.05
    762
    +0.11
    0.05
    Negative Logits
    raints
    -0.73
    CAN
    -0.65
    CRIP
    -0.63
    soDeliveryDate
    -0.63
    Sequ
    -0.62
    alore
    -0.59
    akeru
    -0.59
     Nights
    -0.59
    IONS
    -0.58
     Catal
    -0.57
    POSITIVE LOGITS
     ever
    1.36
     EVER
    1.33
    ever
    1.17
     necessarily
    0.96
    theless
    0.78
     any
    0.75
     condone
    0.75
     Ever
    0.75
     whatsoever
    0.74
     knowingly
    0.74
    Activations Density 0.199%

    No Known Activations