© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 589
    Prev
    Next
    INDEX
    Explanations

    the name "Comey" in text

    oai_token-act-pair · gpt-3.5-turbo

    references to James Comey and related figures in a political context

    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
    land
    -0.63
     farm
    -0.62
     palm
    -0.62
    Mult
    -0.61
     min
    -0.60
     sustainable
    -0.60
     pant
    -0.60
     leg
    -0.60
     tr
    -0.59
     colony
    -0.59
    POSITIVE LOGITS
     Comey
    3.60
     Rosenstein
    1.91
     Clapper
    1.91
    FBI
    1.64
     McCabe
    1.58
     FBI
    1.56
     Priebus
    1.47
     Abedin
    1.47
     Weiner
    1.42
     Mueller
    1.40
    Activations Density 0.018%

    No Known Activations