© 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. 11-RES-JB
    11. 24535
    Prev
    Next
    INDEX
    Explanations

    clauses mentioning an area of expertise or concern

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "of" followed by varying nouns or phrases indicating different areas or fields of interest and concern

    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
    BILL
    -0.73
    GUI
    -0.66
    pieces
    -0.66
    pher
    -0.66
    balls
    -0.64
    aired
    -0.63
    ivan
    -0.62
    pps
    -0.62
    msg
    -0.62
    aciously
    -0.61
    POSITIVE LOGITS
     interest
    1.41
     concern
    1.32
     importance
    1.31
     expertise
    1.27
     prominence
    1.25
     excellence
    1.22
     significance
    1.20
     contention
    1.18
     origin
    1.18
     relevance
    1.13
    Activations Density 0.140%

    No Known Activations