© 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. 7-RES-JB
    11. 7841
    Prev
    Next
    INDEX
    Explanations

    capitalized words related to names or locations

    oai_token-act-pair · gpt-3.5-turbo

    academic or technical jargon that includes abbreviations or terms related to "AG."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gestation
    -0.69
     amen
    -0.69
     psychiat
    -0.69
     favourable
    -0.68
    WARD
    -0.68
     Spock
    -0.67
     responsiveness
    -0.66
     wid
    -0.63
    warm
    -0.62
    EStream
    -0.62
    POSITIVE LOGITS
    ioxide
    0.94
    catentry
    0.87
    irie
    0.81
    ordes
    0.80
    ultural
    0.78
    ulhu
    0.75
    È
    0.74
    rities
    0.73
    asions
    0.73
    enta
    0.73
    Activations Density 0.234%

    No Known Activations