© 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. 11-RES-JB
    11. 7578
    Prev
    Next
    INDEX
    Explanations

    statistics related to numerical proportions

    oai_token-act-pair · gpt-3.5-turbo

    quantified statistics related to fractions or proportions within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unity
    -0.81
    otion
    -0.73
    escription
    -0.70
    sort
    -0.70
    odore
    -0.69
    drawn
    -0.69
    uben
    -0.68
    ̶
    -0.68
    urion
    -0.67
    emption
    -0.67
    POSITIVE LOGITS
     Americans
    1.06
     adults
    1.05
     respondents
    1.03
     households
    0.97
     Britons
    0.95
     Australians
    0.93
     Spani
    0.89
     earners
    0.88
     births
    0.88
     Canadians
    0.87
    Activations Density 0.044%

    No Known Activations