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. 3-RES-JB
    6. 14008
    Prev
    Next
    INDEX
    Explanations

    phrases related to rebukes or sharp criticisms

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "rebuff" and its variations indicating resistance or rejection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lihood
    -0.90
     Kafka
    -0.77
    âĢ¢âĢ¢
    -0.76
     Grail
    -0.66
     Flow
    -0.66
     Dome
    -0.65
     Valhalla
    -0.64
    meal
    -0.63
     Keeper
    -0.62
    teness
    -0.61
    POSITIVE LOGITS
    anche
    1.05
    ounding
    1.04
    uffed
    0.98
     reb
    0.96
    ounded
    0.92
    uked
    0.91
    uls
    0.91
    aul
    0.90
    utations
    0.89
    becca
    0.87
    Activations Density 0.004%

    No Known Activations