© 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. 17741
    Prev
    Next
    INDEX
    Explanations

    terms related to the name "Horace."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to cellular processes and structures

    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
    agers
    -0.79
    ostic
    -0.74
    zag
    -0.73
    agements
    -0.73
    aging
    -0.73
    rd
    -0.71
     barg
    -0.70
    aries
    -0.69
    ect
    -0.68
    ishes
    -0.68
    POSITIVE LOGITS
    llular
    1.02
    llor
    0.92
    llan
    0.89
    lyn
    0.83
    idon
    0.82
    ptives
    0.77
    lla
    0.77
    vich
    0.76
    oute
    0.74
    lli
    0.70
    Activations Density 0.060%

    No Known Activations