© 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. 8247
    Prev
    Next
    INDEX
    Explanations

    concepts related to stereotypes and their effects on behavior and identity

    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
    255
    +0.13
    0.6%
    314
    +0.10
    0.5%
    359
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    654
    +0.13
    0.10
    206
    +0.10
    0.07
    351
    +0.10
    0.10
    Negative Logits
    etsk
    -0.71
     Codex
    -0.66
     Neon
    -0.63
     corridors
    -0.63
     helmets
    -0.62
     Chili
    -0.61
     Encyclopedia
    -0.61
    endiary
    -0.61
     tunnels
    -0.60
     Presidents
    -0.59
    POSITIVE LOGITS
     whichever
    0.93
     claimant
    0.83
    relevant
    0.83
     another
    0.82
     Applicant
    0.82
     nearby
    0.80
     adjacent
    0.80
     opposite
    0.79
     competitor
    0.79
     nearest
    0.78
    Activations Density 6.296%

    No Known Activations