© 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. 11-RES-JB
    11. 7633
    Prev
    Next
    INDEX
    Explanations

    the phrase "First of all."

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "first of all" or similar introductory phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    obal
    -0.73
    rams
    -0.64
    orous
    -0.63
    ularity
    -0.61
    weeney
    -0.61
    ores
    -0.61
    omas
    -0.61
    chrom
    -0.60
    arial
    -0.60
    ADRA
    -0.58
    POSITIVE LOGITS
     foremost
    0.99
     kin
    0.97
     all
    0.89
     equals
    0.83
     ali
    0.82
     COUR
    0.72
    ortunately
    0.71
     course
    0.69
    ELY
    0.68
     necessity
    0.65
    Activations Density 0.037%

    No Known Activations