© 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. 6-RES-JB
    11. 18837
    Prev
    Next
    INDEX
    Explanations

    mentions of police or military operations entailing a raid or seizure

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "raid."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chell
    -0.68
     Gork
    -0.63
    DonaldTrump
    -0.63
     Leilan
    -0.61
     Genie
    -0.61
     Quincy
    -0.60
    Ian
    -0.60
    Fed
    -0.60
    mitt
    -0.60
    rouch
    -0.60
    POSITIVE LOGITS
     raid
    0.95
     raids
    0.95
    Raid
    0.88
     raided
    0.86
     raiding
    0.85
    ishly
    0.84
    nard
    0.79
    ers
    0.78
    iversary
    0.78
     sweeps
    0.74
    Activations Density 0.023%

    No Known Activations