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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-RES-JB
    6. 15864
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Doc" with various numerical ratings, potentially referring to different individuals/entities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Doc" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    places
    -0.77
     advis
    -0.69
     boarding
    -0.67
     Admir
    -0.66
     Mechdragon
    -0.64
    boarding
    -0.62
     Royale
    -0.60
    theless
    -0.60
    FUL
    -0.59
     perme
    -0.59
    POSITIVE LOGITS
    herty
    1.37
    uments
    1.33
    omo
    1.12
    ents
    1.08
    ility
    1.02
    umen
    0.99
    iencies
    0.95
    ual
    0.91
    sis
    0.91
    ilt
    0.87
    Activations Density 0.025%

    No Known Activations