© 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. 19300
    Prev
    Next
    INDEX
    Explanations

    words indicating a call to action or suggestion to the reader

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "have" and related phrases

    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
    anism
    -0.73
     appell
    -0.66
    ô
    -0.66
    cules
    -0.65
     matters
    -0.65
    Islamic
    -0.64
    upon
    -0.64
     organs
    -0.64
     objectionable
    -0.64
     irregularities
    -0.63
    POSITIVE LOGITS
     couple
    1.18
     few
    1.14
     bunch
    1.11
     lot
    0.97
     handful
    0.96
     dozen
    0.91
    uras
    0.89
     friend
    0.87
     bit
    0.83
     glimpse
    0.82
    Activations Density 0.345%

    No Known Activations