© 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. 1104
    Prev
    Next
    INDEX
    Explanations

    words related to security guards

    oai_token-act-pair · gpt-3.5-turbo

    references to security personnel or guards

    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
     Sketch
    -0.75
    conom
    -0.71
     Katy
    -0.69
    luence
    -0.67
    commercial
    -0.67
    category
    -0.64
    à¤
    -0.64
    version
    -0.63
    REE
    -0.63
    historic
    -0.63
    POSITIVE LOGITS
     guards
    3.84
    guards
    2.77
     Guards
    2.72
     guard
    2.61
     Guard
    1.98
    guard
    1.76
     guarding
    1.71
     patrols
    1.66
     guarded
    1.56
     robbers
    1.49
    Activations Density 0.014%

    No Known Activations