© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 10596
    Prev
    Next
    INDEX
    Explanations

    names of famous people and groups in different fields such as sports, music, and politics

    oai_token-act-pair · gpt-3.5-turbo

    references to various roles and identities in the entertainment and sports industries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sole
    -0.70
    consumer
    -0.69
    Security
    -0.68
    potion
    -0.66
    votes
    -0.66
    UTH
    -0.66
    âķ
    -0.65
    wp
    -0.65
    payer
    -0.65
    Scient
    -0.65
    POSITIVE LOGITS
    hips
    1.14
    hip
    1.04
     alike
    0.88
    paces
    0.86
     Archie
    0.82
     such
    0.81
     Axel
    0.80
    hots
    0.79
     Sonny
    0.79
     collide
    0.78
    Activations Density 0.470%

    No Known Activations