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. 10-RES-JB
    6. 9113
    Prev
    Next
    INDEX
    Explanations

    words that are used to emphasize a point or add emphasis to a statement

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the word "all."

    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
    ciation
    -0.68
    bal
    -0.60
    rir
    -0.59
    pton
    -0.57
    OUNT
    -0.57
    assembly
    -0.57
    EStream
    -0.56
    dl
    -0.55
    lic
    -0.55
    utch
    -0.54
    POSITIVE LOGITS
    owing
    1.44
    iances
    1.30
    iance
    1.17
    owed
    1.16
    ergic
    1.14
    ocate
    1.07
    ergy
    1.06
    uding
    1.05
    yson
    1.03
    ocations
    1.02
    Activations Density 0.075%

    No Known Activations