© 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. 2443
    Prev
    Next
    INDEX
    Explanations

    key terms related to writers and their works

    oai_token-act-pair · gpt-3.5-turbo

    terms related to writers and writing

    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
    rals
    -0.79
    illon
    -0.77
     Lumpur
    -0.74
    ADRA
    -0.71
    Ĭ±
    -0.70
    essage
    -0.66
    tnc
    -0.66
    ptions
    -0.65
     CCTV
    -0.65
    ibaba
    -0.65
    POSITIVE LOGITS
    writing
    0.99
    writer
    0.95
    writ
    0.93
     laureate
    0.92
    uscript
    0.87
     fiction
    0.85
     Beware
    0.84
    writers
    0.83
    pub
    0.79
     writer
    0.78
    Activations Density 0.054%

    No Known Activations