© 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. 10-RES-JB
    11. 6590
    Prev
    Next
    INDEX
    Explanations

    numerical details related to accidents or incidents involving a group of individuals

    oai_token-act-pair · gpt-3.5-turbo

    numerical references to quantities and counts of individuals involved in events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ´ãĥ³
    -0.84
    omics
    -0.78
    feature
    -0.72
    $$
    -0.71
    Rating
    -0.70
     tremend
    -0.70
    answer
    -0.69
    Token
    -0.69
    ULE
    -0.69
    unct
    -0.68
    POSITIVE LOGITS
     occupants
    1.25
    teen
    1.13
     assailants
    1.10
     policemen
    1.09
     persons
    1.08
     unidentified
    1.08
     others
    1.04
     attackers
    1.04
     witnesses
    1.02
     males
    1.02
    Activations Density 0.125%

    No Known Activations