Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 15329
    Prev
    Next
    INDEX
    Explanations

    titles or roles with the word "vice president"

    oai_token-act-pair · gpt-3.5-turbo

    titles or positions related to vice presidency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tics
    -0.82
     Locked
    -0.68
     fingerprints
    -0.66
     Escape
    -0.65
     Drift
    -0.64
     Flu
    -0.62
     Tatt
    -0.60
     Hour
    -0.59
    nikov
    -0.59
     Trials
    -0.58
    POSITIVE LOGITS
     president
    1.28
    president
    1.26
     chairman
    1.17
     chancellor
    1.14
    chair
    1.14
     chair
    1.08
     versa
    1.04
     dean
    0.99
    founder
    0.94
    director
    0.91
    Activations Density 0.017%

    No Known Activations