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. 24268
    Prev
    Next
    INDEX
    Explanations

    phrases expressing doubts or disagreements with a particular proposal or situation

    oai_token-act-pair · gpt-3.5-turbo

    conversational phrases and dialogue elements

    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
    etheless
    -0.88
    quickShipAvailable
    -0.85
    Contents
    -0.77
    ometimes
    -0.72
    channelAvailability
    -0.70
    Pand
    -0.67
    ĵĺ
    -0.67
    ioned
    -0.67
    Truth
    -0.67
    unal
    -0.67
    POSITIVE LOGITS
    '."
    1.66
    .'"
    1.58
    ,'"
    1.58
    ',"
    1.56
    !'"
    1.56
    ?'"
    1.53
    '"
    1.37
    ']
    1.14
    ').
    1.06
    ?'
    1.02
    Activations Density 0.290%

    No Known Activations