© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9-RES-JB
    11. 7613
    Prev
    Next
    INDEX
    Explanations

    names of authors in scientific studies

    oai_token-act-pair · gpt-3.5-turbo

    references to authors and their contributions in scientific studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    netflix
    -0.83
    soType
    -0.75
    deal
    -0.72
     decency
    -0.71
     lockout
    -0.70
    atism
    -0.69
    wagon
    -0.68
    Rules
    -0.68
     repeal
    -0.67
    twitch
    -0.67
    POSITIVE LOGITS
     researchers
    1.39
     doctoral
    1.32
     researcher
    1.29
     scientists
    1.29
     PhD
    1.28
     physicists
    1.25
     scientist
    1.18
     biologist
    1.15
     Researchers
    1.14
     collaborators
    1.14
    Activations Density 0.423%

    No Known Activations