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. 7-RES-JB
    6. 17466
    Prev
    Next
    INDEX
    Explanations

    instances of contrasting or contrasting ideas

    oai_token-act-pair · gpt-3.5-turbo

    the word "while" and its variations to indicate contrasting scenarios or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilet
    -0.73
    Lay
    -0.66
    orthy
    -0.65
    bard
    -0.64
    atari
    -0.64
    INS
    -0.63
    aeda
    -0.63
    inated
    -0.63
    idy
    -0.62
    ANN
    -0.62
    POSITIVE LOGITS
     acknowledging
    0.94
     technically
    0.80
     respecting
    0.80
     conced
    0.77
     researching
    0.74
     admitting
    0.74
     imperfect
    0.72
    terness
    0.67
     shading
    0.67
    lihood
    0.66
    Activations Density 0.070%

    No Known Activations