Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 15267
    Prev
    Next
    INDEX
    Explanations

    names and terms related to a specific person or entity, likely someone named "Ulbricht."

    oai_token-act-pair · gpt-3.5-turbo

    names and references to specific individuals related to criminal or investigative 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
    externalActionCode
    -0.93
    displayText
    -0.84
     Responsibility
    -0.75
     Continued
    -0.74
     Marketable
    -0.70
    soDeliveryDate
    -0.70
    ãģĨ
    -0.67
     EDT
    -0.67
    BOOK
    -0.66
     Particip
    -0.66
    POSITIVE LOGITS
     Ul
    1.25
    gew
    1.01
    Ul
    1.00
    ldom
    0.95
     intrins
    0.90
    ricular
    0.88
    grim
    0.85
    rica
    0.85
    ailability
    0.85
    aeper
    0.84
    Activations Density 0.006%

    No Known Activations