© 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. 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. 23917
    Prev
    Next
    INDEX
    Explanations

    comparisons and evaluations involving the degree or quantity of actions or effects

    oai_token-act-pair · gpt-3.5-turbo

    expressions of excess or inadequacy in terms of actions or contributions

    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
    urated
    -0.73
    jected
    -0.70
     Fever
    -0.70
     Reaction
    -0.66
     Ticket
    -0.63
    etus
    -0.62
    gypt
    -0.61
    Sah
    -0.60
     Clin
    -0.60
     Persons
    -0.59
    POSITIVE LOGITS
     outreach
    0.97
     homework
    0.89
     harm
    0.86
     damage
    0.85
     grunt
    0.84
    duty
    0.80
     chores
    0.80
    research
    0.80
     research
    0.80
     groundwork
    0.79
    Activations Density 0.140%

    No Known Activations