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. 1-RES-JB
    6. 1854
    Prev
    Next
    INDEX
    Explanations

    the word "Yeah" with varying levels of emphasis

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "Yeah" indicating agreement or affirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RAW
    -0.78
    tein
    -0.77
     ILCS
    -0.77
    cycl
    -0.75
    resp
    -0.73
    ersive
    -0.71
    venant
    -0.69
    apers
    -0.69
    cele
    -0.69
    aukee
    -0.68
    POSITIVE LOGITS
     Yeah
    1.34
    yeah
    1.14
     yeah
    1.10
    Yeah
    1.04
    terday
    1.02
     pardon
    0.94
    hhhh
    0.89
     Yep
    0.87
     Alright
    0.84
     Nope
    0.82
    Activations Density 0.009%

    No Known Activations