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. 17415
    Prev
    Next
    INDEX
    Explanations

    countries and territories

    oai_token-act-pair · gpt-3.5-turbo

    references to specific countries and discussions of societal issues or diseases metaphorically described as "plagues."

    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
    arity
    -0.72
     finishes
    -0.71
     Unch
    -0.69
     Lah
    -0.69
     Bucc
    -0.67
    ãģ®éŃĶ
    -0.67
     Univ
    -0.67
     MLB
    -0.67
    vind
    -0.66
    ificantly
    -0.66
    POSITIVE LOGITS
     rabbit
    1.79
     plague
    1.62
     Guinea
    1.62
     fox
    1.57
     swamp
    1.45
     Congo
    1.44
     pigeon
    1.38
     rabbits
    1.38
     carrot
    1.36
     peg
    1.32
    Activations Density 0.046%

    No Known Activations