© 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. 9-RES-JB
    11. 4824
    Prev
    Next
    INDEX
    Explanations

    words related to undercover operations or investigations

    oai_token-act-pair · gpt-3.5-turbo

    instances of undercover operations or agents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hement
    -0.75
    ettle
    -0.75
    reciation
    -0.74
    idian
    -0.74
    gran
    -0.73
    pite
    -0.73
    yards
    -0.72
    plex
    -0.71
    jri
    -0.70
    estone
    -0.70
    POSITIVE LOGITS
     operatives
    0.94
     informant
    0.89
     CIA
    0.86
     FBI
    0.86
     investigator
    0.85
     officer
    0.82
     operation
    0.82
     operative
    0.80
     detective
    0.79
     Operation
    0.78
    Activations Density 0.086%

    No Known Activations