© 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. 10-RES-JB
    11. 17316
    Prev
    Next
    INDEX
    Explanations

    phrases using the term "across the board"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "across the board."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icho
    -0.72
    BIL
    -0.70
    ISON
    -0.67
    nery
    -0.63
    Anonymous
    -0.63
    RESULTS
    -0.62
    aciously
    -0.62
    manship
    -0.61
    uning
    -0.61
     Akin
    -0.60
    POSITIVE LOGITS
     globe
    1.31
     spectrum
    1.30
     board
    1.20
     breadth
    1.15
     aisle
    1.15
     continent
    1.08
     continuum
    1.05
     country
    1.04
     entire
    1.04
     entirety
    1.02
    Activations Density 0.070%

    No Known Activations