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

    Neuronpedia

    APICircuit 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. 10-RES-JB
    6. 302
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a need for caution or preparation before taking a specific action

    oai_token-act-pair · gpt-3.5-turbo

    the word "before" in various contexts, indicating caution or a need for prior assessment

    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
    geist
    -0.72
    atic
    -0.71
    ãĥķãĤ©
    -0.70
    OTOS
    -0.69
    odied
    -0.67
    hid
    -0.66
    fighter
    -0.66
    arious
    -0.66
    bern
    -0.64
    OGR
    -0.64
    POSITIVE LOGITS
     proceeding
    1.55
     committing
    1.39
     deciding
    1.35
     embark
    1.24
     submitting
    1.22
     attempting
    1.22
     entering
    1.20
     undertaking
    1.20
     initiating
    1.19
     agreeing
    1.14
    Activations Density 0.070%

    No Known Activations