© 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 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. 3327
    Prev
    Next
    INDEX
    Explanations

    phrases related to the history or track record of individuals or entities

    oai_token-act-pair · gpt-3.5-turbo
    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
    ishable
    -0.74
    Flow
    -0.71
    wolves
    -0.70
    Sport
    -0.69
    ateurs
    -0.68
    ij士
    -0.66
    uri
    -0.65
    Stars
    -0.64
    idden
    -0.64
    ishers
    -0.63
    POSITIVE LOGITS
     dating
    0.93
     spanning
    0.82
     revolving
    0.81
     associ
    0.77
     of
    0.74
     dealing
    0.74
     supporting
    0.74
     favoring
    0.73
     advocating
    0.73
     exposing
    0.73
    Activations Density 0.053%

    No Known Activations