© 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. 8-RES-JB
    11. 18468
    Prev
    Next
    INDEX
    Explanations

    statements emphasizing what is known or certain

    oai_token-act-pair · gpt-3.5-turbo

    phrases asserting knowledge or certainty about various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pex
    -0.93
    ksh
    -0.75
    osi
    -0.73
    onies
    -0.70
    ermanent
    -0.70
    rentice
    -0.68
    cohol
    -0.68
    onial
    -0.65
    oling
    -0.64
    inance
    -0.64
    POSITIVE LOGITS
     ourselves
    0.92
     how
    0.85
     beforehand
    0.80
    ledged
    0.72
    ledge
    0.72
     anecd
    0.68
     guesses
    0.68
    lege
    0.68
    ETH
    0.68
     definitively
    0.67
    Activations Density 0.092%

    No Known Activations