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. 8-RES-JB
    6. 5643
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Calvin" and related terms like "badge", "wrist", and "watch"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Calvin" and terms related to badges and wrist accessories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rative
    -0.86
    emort
    -0.85
    rigan
    -0.85
    rology
    -0.82
    rov
    -0.77
    rolog
    -0.77
    yre
    -0.76
    irez
    -0.74
    imbabwe
    -0.73
    sburg
    -0.73
    POSITIVE LOGITS
    bands
    0.91
    strap
    0.81
    umper
    0.77
     buckle
    0.72
     bracelet
    0.72
    band
    0.70
    links
    0.69
    oute
    0.67
     straps
    0.65
    NRS
    0.63
    Activations Density 0.074%

    No Known Activations