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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 10-RES-JB
    6. 8799
    Prev
    Next
    INDEX
    Explanations

    comparative statements related to choices or decision-making

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to decision-making and personal choice

    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
    esc
    -0.67
    TPS
    -0.66
    SourceFile
    -0.66
    aunt
    -0.64
    comed
    -0.63
    EH
    -0.60
    cia
    -0.60
    iazep
    -0.59
    hello
    -0.59
    stros
    -0.59
    POSITIVE LOGITS
     deciding
    1.54
     decide
    1.46
     decisions
    1.45
     determine
    1.36
     determining
    1.35
     decision
    1.33
     determines
    1.32
     deliberations
    1.21
     undecided
    1.20
     choice
    1.20
    Activations Density 1.191%

    No Known Activations