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. 10162
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a condition or exception

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "unless" and its variations, indicating conditional statements or exceptions

    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
    ery
    -0.80
    sequence
    -0.75
    ulate
    -0.73
    ruary
    -0.72
    eph
    -0.72
    08
    -0.69
    ARC
    -0.69
    entry
    -0.68
    eny
    -0.68
    eries
    -0.67
    POSITIVE LOGITS
     otherwise
    1.02
    soever
    0.89
     expressly
    0.76
    wcsstore
    0.71
     corrective
    0.71
     indemn
    0.70
     necessary
    0.70
    fy
    0.70
     explicitly
    0.67
     you
    0.67
    Activations Density 0.016%

    No Known Activations