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

    Neuronpedia

    Jacobian LensNEW
    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. 8-RES-JB
    11. 19309
    Prev
    Next
    INDEX
    Explanations

    scientific studies or research findings

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "that" indicating findings or conclusions in research statements

    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
    iciary
    -0.77
    atro
    -0.70
    arted
    -0.69
    oses
    -0.67
    andem
    -0.65
    ETA
    -0.65
    arak
    -0.62
    Guard
    -0.62
    BuyableInstoreAndOnline
    -0.62
    gur
    -0.61
    POSITIVE LOGITS
     although
    1.01
     whereas
    0.85
     despite
    0.83
     there
    0.80
     "[
    0.77
     unlike
    0.73
     whilst
    0.72
     respondents
    0.71
     contrary
    0.71
     they
    0.70
    Activations Density 0.178%

    No Known Activations