© 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. 11290
    Prev
    Next
    INDEX
    Explanations

    percentages and fractions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that refer to statistical data or percentages

    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
    sort
    -0.79
    Clar
    -0.75
    nah
    -0.74
    antic
    -0.73
    cule
    -0.72
    ENCE
    -0.71
    otion
    -0.69
    elf
    -0.69
    der
    -0.68
    ibe
    -0.67
    POSITIVE LOGITS
     respondents
    1.34
     households
    1.13
     Americans
    1.01
     those
    0.97
     surveyed
    0.95
     earners
    0.93
     applicants
    0.92
     eligible
    0.91
     Britons
    0.91
     participants
    0.90
    Activations Density 0.110%

    No Known Activations