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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 22684
    Prev
    Next
    INDEX
    Explanations

    historic challenges or instances where individuals are being pushed to prove or defend something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "challenge" and its variations

    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
    abet
    -0.87
    nect
    -0.76
    gas
    -0.74
    otide
    -0.73
    ophe
    -0.71
    ahon
    -0.70
    gap
    -0.68
    translation
    -0.68
    ibrary
    -0.67
    Split
    -0.66
    POSITIVE LOGITS
    enged
    0.86
     incumb
    0.76
     challenging
    0.74
     challengers
    0.73
    ioned
    0.71
     challenged
    0.70
    ingly
    0.70
     him
    0.70
     unanswered
    0.68
     challenges
    0.68
    Activations Density 0.022%

    No Known Activations