© 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. 10-RES-JB
    11. 19008
    Prev
    Next
    INDEX
    Explanations

    phrases indicating knowledge or familiarity with a topic

    oai_token-act-pair · gpt-3.5-turbo

    statements indicating shared knowledge or common understanding among the audience

    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
    oreal
    -0.80
    cific
    -0.73
    ngth
    -0.69
     streng
    -0.69
    rontal
    -0.68
    vati
    -0.67
    orthy
    -0.66
    ongevity
    -0.65
    ihad
    -0.64
    bably
    -0.64
    POSITIVE LOGITS
    tale
    0.76
     about
    0.68
     how
    0.67
     that
    0.67
     by
    0.63
     why
    0.60
    anton
    0.59
     tales
    0.58
     Ced
    0.57
     what
    0.56
    Activations Density 0.126%

    No Known Activations