© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 3056
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Deputy" combined with the high numerical value of 9 or 10

    oai_token-act-pair · gpt-3.5-turbo

    references to the title "Deputy" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gutenberg
    -0.93
    stakes
    -0.83
    hetti
    -0.81
    oring
    -0.80
    ipedia
    -0.78
    orem
    -0.77
    ĸļ
    -0.76
    olen
    -0.74
    ouring
    -0.71
    ograph
    -0.71
    POSITIVE LOGITS
    uty
    0.93
     sher
    0.90
     clerks
    0.88
     deputy
    0.87
     assistant
    0.85
     sheriff
    0.85
     adjunct
    0.82
    chief
    0.79
     director
    0.78
     editor
    0.74
    Activations Density 0.025%

    No Known Activations