© 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. 1-RES-JB
    11. 3273
    Prev
    Next
    INDEX
    Explanations

    phrases related to emotion, genetic programs, and explanations

    oai_token-act-pair · gpt-3.5-turbo

    references to emotional and social expression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Thousand
    -0.72
    Ń·
    -0.71
    ether
    -0.70
     Brewers
    -0.70
     Shades
    -0.69
    sonian
    -0.68
    END
    -0.64
     Bullets
    -0.64
    ETA
    -0.63
    ICK
    -0.60
    POSITIVE LOGITS
     expression
    1.24
    terday
    1.23
     expressions
    1.08
     Expression
    1.00
    expression
    0.88
     ende
    0.85
     guiActiveUn
    0.85
    ively
    0.76
    express
    0.74
    ogenesis
    0.73
    Activations Density 0.012%

    No Known Activations