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. 8-RES-JB
    6. 3635
    Prev
    Next
    INDEX
    Explanations

    options or choices based on a specific situation or preference

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to decision-making and choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    akov
    -0.80
    mining
    -0.78
    lying
    -0.73
    scripts
    -0.72
    orget
    -0.69
    izons
    -0.67
    ertodd
    -0.66
    ©¶æ¥µ
    -0.66
    roxy
    -0.66
    raid
    -0.66
    POSITIVE LOGITS
     closest
    1.02
     nearest
    1.00
     weakest
    0.95
     best
    0.93
     hardest
    0.93
     safest
    0.92
     strongest
    0.92
     quickest
    0.92
     cheapest
    0.87
     happiest
    0.87
    Activations Density 0.500%

    No Known Activations