© 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. 17235
    Prev
    Next
    INDEX
    Explanations

    references to the company Oracle and its founder Larry Ellison

    oai_token-act-pair · gpt-3.5-turbo

    references to Oracle and its key figures, particularly Larry Ellison

    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
    ly
    -0.79
    fully
    -0.77
    erate
    -0.76
    stem
    -0.74
    mble
    -0.73
    elsius
    -0.73
    line
    -0.71
    LINE
    -0.71
    rences
    -0.70
    ew
    -0.69
    POSITIVE LOGITS
     Printed
    0.81
     Oracle
    0.80
    ificial
    0.74
    emonium
    0.71
     Pharmaceutical
    0.68
     rewritten
    0.68
     Slayer
    0.68
     Arena
    0.67
    helps
    0.67
    ozo
    0.66
    Activations Density 0.074%

    No Known Activations