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

    Neuronpedia

    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. 9-RES-JB
    11. 7588
    Prev
    Next
    INDEX
    Explanations

    instances of words related to strong reasoning or arguments

    oai_token-act-pair · gpt-3.5-turbo

    expressions of strong interest or persuasive arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hops
    -0.92
    sterdam
    -0.77
    keepers
    -0.69
    paces
    -0.69
    chie
    -0.67
    hop
    -0.66
    isites
    -0.63
    clair
    -0.63
    usterity
    -0.62
    keeper
    -0.62
    POSITIVE LOGITS
    ibly
    1.09
     proofs
    0.95
     evidence
    0.93
     arguments
    0.91
    ingly
    0.91
     argument
    0.90
    ly
    0.88
    ible
    0.87
     proof
    0.86
    evidence
    0.86
    Activations Density 0.104%

    No Known Activations