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. 13034
    Prev
    Next
    INDEX
    Explanations

    phrases related to decision-making and choices

    oai_token-act-pair · gpt-3.5-turbo

    phrases and actions related to decision-making and taking action

    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
     vividly
    -0.73
    clips
    -0.60
    Definition
    -0.59
     truths
    -0.58
     (<
    -0.57
    inguished
    -0.56
     WATCHED
    -0.56
    orate
    -0.56
    comments
    -0.56
    jri
    -0.56
    POSITIVE LOGITS
     Option
    0.79
     elsewhere
    0.77
     gamble
    0.74
    Option
    0.73
     swoop
    0.70
     sooner
    0.68
     outright
    0.67
    cedes
    0.67
     reneg
    0.66
    rieg
    0.66
    Activations Density 0.323%

    No Known Activations