© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 26218
    Prev
    Next
    INDEX
    Explanations

    statements about the nature and measurement of intelligence and its relationship to culture and societal norms

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    642
    +0.14
    0.6%
    7
    +0.13
    0.6%
    255
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    7
    +0.14
    0.16
    102
    +0.13
    0.14
    540
    +0.11
    0.13
    Negative Logits
    adelphia
    -0.83
    enaries
    -0.74
    racuse
    -0.73
     Tackle
    -0.72
    Town
    -0.72
    culosis
    -0.71
    venture
    -0.71
    ventures
    -0.70
     Shots
    -0.70
    anwhile
    -0.70
    POSITIVE LOGITS
    omorphic
    1.24
     metaph
    1.15
     logically
    1.14
     observable
    1.13
     meaningless
    1.13
     implied
    1.12
     relational
    1.10
     subjective
    1.09
     mediated
    1.08
     ambiguous
    1.07
    Activations Density 0.891%

    No Known Activations