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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 14544
    Prev
    Next
    INDEX
    Explanations

    phrases related to having no hesitation to perform an action

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating certainty or a lack of hesitation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arov
    -0.67
    EStream
    -0.61
    Downloadha
    -0.58
    obal
    -0.58
    glomer
    -0.57
    ossible
    -0.57
    ode
    -0.56
     teasp
    -0.56
    Nev
    -0.55
    Network
    -0.54
    POSITIVE LOGITS
    mberg
    0.81
    -->
    0.75
    kers
    0.71
     tragedies
    0.68
    iery
    0.68
    steen
    0.65
     Stras
    0.65
    lein
    0.63
    ingen
    0.62
    amaz
    0.61
    Activations Density 0.223%

    No Known Activations