© 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. 10970
    Prev
    Next
    INDEX
    Explanations

    names of government offices

    oai_token-act-pair · gpt-3.5-turbo

    references to various offices associated with legal and governmental entities

    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
    Movie
    -0.71
    oise
    -0.68
    Grade
    -0.65
    200000
    -0.65
    NetMessage
    -0.63
    isable
    -0.63
     epoch
    -0.63
    schild
    -0.63
    mere
    -0.63
    isers
    -0.62
    POSITIVE LOGITS
     prosec
    0.91
     raided
    0.74
     Cheong
    0.72
     clerk
    0.72
    room
    0.71
     intervened
    0.70
     Press
    0.69
     prosecuted
    0.68
     alleges
    0.67
    press
    0.66
    Activations Density 0.045%

    No Known Activations