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. 0-RES-JB
    6. 3937
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to individuals, especially including the surname "agan"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Kagan."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     daily
    -0.66
    ,...
    -0.63
     negligence
    -0.61
     IP
    -0.59
    XXX
    -0.58
     meth
    -0.58
     istg
    -0.57
     pound
    -0.56
     attached
    -0.56
     worldwide
    -0.56
    POSITIVE LOGITS
    agan
    4.82
    aghan
    1.41
    agen
    1.27
    igan
    1.26
    agher
    1.20
    ahan
    1.19
    gan
    1.17
    aga
    1.16
    agh
    1.14
    ago
    1.12
    Activations Density 0.007%

    No Known Activations