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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 4-RES-JB
    6. 12633
    Prev
    Next
    INDEX
    Explanations

    uncertainty about future events or outcomes

    oai_token-act-pair · gpt-3.5-turbo

    expressions conveying uncertainty or unpredictability about knowledge and experiences

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

    No Comments

    Negative Logits
     antioxid
    -0.67
     slide
    -0.61
     some
    -0.60
     SetTextColor
    -0.59
     Crusader
    -0.59
    hai
    -0.59
     Literary
    -0.57
    lyak
    -0.56
    yip
    -0.56
     Bryant
    -0.55
    POSITIVE LOGITS
    rences
    1.07
    theless
    1.06
     nor
    0.94
    rency
    0.83
    cation
    0.73
    ounter
    0.73
    ORED
    0.71
     dreamed
    0.69
     EVER
    0.69
    ounters
    0.68
    Activations Density 0.088%

    No Known Activations