© 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. 18976
    Prev
    Next
    INDEX
    Explanations

    names of characters or entities within a story

    oai_token-act-pair · gpt-3.5-turbo

    specific character names and their roles in a narrative

    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
    Repeat
    -0.83
    Total
    -0.76
    Depth
    -0.73
    ulatory
    -0.71
    icol
    -0.70
    cussion
    -0.69
    Semitic
    -0.69
     NUM
    -0.68
    IFIED
    -0.68
    valued
    -0.68
    POSITIVE LOGITS
     discovers
    1.71
     learns
    1.55
     confronts
    1.44
     escapes
    1.38
     realizes
    1.35
     convin
    1.34
     decides
    1.33
     wakes
    1.32
     encounters
    1.29
     unwittingly
    1.25
    Activations Density 0.326%

    No Known Activations