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. 4-RES-JB
    6. 17426
    Prev
    Next
    INDEX
    Explanations

    proper nouns indicating specific individuals involved in criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the definite article "the."

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

    No Comments

    Negative Logits
    omics
    -0.78
    Chart
    -0.69
    thood
    -0.69
    govtrack
    -0.67
    warts
    -0.67
     ç¥ŀ
    -0.66
    liam
    -0.66
    ageddon
    -0.65
    anguage
    -0.64
    joice
    -0.64
    POSITIVE LOGITS
     latter
    1.19
     same
    1.16
     alleged
    1.08
     aforementioned
    1.02
     deadliest
    1.02
     incident
    0.99
     youngest
    0.98
     heaviest
    0.96
     FBI
    0.95
     latest
    0.94
    Activations Density 1.099%

    No Known Activations