© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 20482
    Prev
    Next
    INDEX
    Explanations

    Specific symbols, likely related to a particular type of categorization or classification

    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
     adm
    -0.79
     phyl
    -0.76
     diplom
    -0.72
    ģĸ
    -0.68
    thumbnails
    -0.68
     roy
    -0.67
     afore
    -0.64
     variables
    -0.64
     Geral
    -0.64
     Miko
    -0.63
    POSITIVE LOGITS
    ossible
    1.39
    redict
    1.37
    ossibly
    1.31
    rotein
    1.28
    ossession
    1.26
    ractical
    1.25
    assion
    1.25
    owered
    1.25
    ropri
    1.25
    ulse
    1.25
    Activations Density 0.037%

    No Known Activations