© 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. 1-RES-JB
    11. 14329
    Prev
    Next
    INDEX
    Explanations

    mentions of writers and their related activities

    oai_token-act-pair · gpt-3.5-turbo

    references to writers or their roles in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    undai
    -0.93
    ibaba
    -0.81
    xon
    -0.79
     Lumpur
    -0.78
    rals
    -0.77
    illon
    -0.74
    inho
    -0.73
    umph
    -0.71
    opping
    -0.70
    Ĭ±
    -0.70
    POSITIVE LOGITS
     writer
    1.23
    writer
    1.07
     laureate
    1.04
     writers
    1.03
     Writer
    0.95
    writ
    0.93
    writers
    0.88
     Writers
    0.86
     fiction
    0.84
    writing
    0.82
    Activations Density 0.020%

    No Known Activations