© 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. 18472
    Prev
    Next
    INDEX
    Explanations

    mentions of high-ranking governmental officials, specifically Secretaries of State

    oai_token-act-pair · gpt-3.5-turbo

    references to government officials in their respective roles

    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
    liga
    -0.71
    riks
    -0.71
    ãĤ¤ãĥĪ
    -0.67
    Ô
    -0.66
    plet
    -0.65
    ersen
    -0.64
     Crew
    -0.64
    xtap
    -0.64
    pload
    -0.63
     mos
    -0.62
    POSITIVE LOGITS
     Merrill
    0.84
     Benedict
    0.75
     Treasury
    0.72
    arations
    0.72
     Tillerson
    0.70
     Theresa
    0.69
    aration
    0.69
    ference
    0.69
    ATES
    0.67
     nominee
    0.65
    Activations Density 0.018%

    No Known Activations