© 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. 7964
    Prev
    Next
    INDEX
    Explanations

    references to the CIA

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the CIA

    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
     âĹ
    -0.80
    à¼
    -0.72
    Ö
    -0.72
    eng
    -0.72
    imer
    -0.69
    omy
    -0.69
    oken
    -0.67
    ã
    -0.67
    hei
    -0.66
    âĹ
    -0.64
    POSITIVE LOGITS
     CIA
    3.47
    CIA
    3.14
     KGB
    2.01
     FBI
    1.87
     DEA
    1.82
     NSA
    1.79
    FBI
    1.75
    NSA
    1.48
     USAF
    1.45
     JFK
    1.44
    Activations Density 0.018%

    No Known Activations