© 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. 8-RES-JB
    11. 4286
    Prev
    Next
    INDEX
    Explanations

    editor's notes in articles

    oai_token-act-pair · gpt-3.5-turbo

    references and mentions of editors within the text

    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
     Sicily
    -0.64
    metics
    -0.63
    romy
    -0.61
    ulhu
    -0.59
    20439
    -0.59
    llular
    -0.57
    abouts
    -0.57
     SEAL
    -0.57
     diabetic
    -0.57
    clus
    -0.56
    POSITIVE LOGITS
    ial
    0.90
    iversary
    0.83
     Picks
    0.83
     Note
    0.77
    ially
    0.77
     Comments
    0.74
     Supported
    0.73
    ickson
    0.72
    icularly
    0.72
    iffe
    0.72
    Activations Density 0.050%

    No Known Activations