© 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. 16276
    Prev
    Next
    INDEX
    Explanations

    references to literary or journalistic reviews

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various reviews, particularly in the context of publications

    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
    llular
    -0.82
    bestos
    -0.72
    ktop
    -0.71
    lt
    -0.69
    cot
    -0.68
    inav
    -0.68
    BuyableInstoreAndOnline
    -0.67
    LM
    -0.66
    othing
    -0.63
    xon
    -0.63
    POSITIVE LOGITS
     Review
    1.44
     Reviews
    1.28
    Review
    1.12
    Reviewed
    1.09
    review
    1.01
     reviews
    0.98
     Rating
    0.96
     Transcript
    0.94
     reviewer
    0.89
     Roundup
    0.89
    Activations Density 0.006%

    No Known Activations