© 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. 4-RES-JB
    11. 14768
    Prev
    Next
    INDEX
    Explanations

    instances of covert operations or activities

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with covert operations or secretive activities

    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
     Pwr
    -0.84
    ð
    -0.82
     Atkinson
    -0.81
    idian
    -0.72
    Interstitial
    -0.70
    ordan
    -0.69
    alon
    -0.69
    itar
    -0.67
    ĪĴ
    -0.66
    ICAN
    -0.66
    POSITIVE LOGITS
     covert
    0.87
     spy
    0.86
     spies
    0.84
    ovie
    0.84
     plotting
    0.82
    arial
    0.82
     infiltr
    0.81
     annex
    0.80
     secretly
    0.79
     camoufl
    0.77
    Activations Density 0.017%

    No Known Activations