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. 14082
    Prev
    Next
    INDEX
    Explanations

    words related to time progression or advancement

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of "fast food" and the expression "fast forward."

    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
     kindred
    -0.80
    Ö¼
    -0.78
    ById
    -0.77
    ±
    -0.72
     Loren
    -0.72
     Contributions
    -0.72
    ³
    -0.71
    ENA
    -0.69
    ¶
    -0.67
    Lenin
    -0.67
    POSITIVE LOGITS
    ounters
    0.83
    charging
    0.77
     uptake
    0.74
    steen
    0.73
    itiveness
    0.71
    cil
    0.69
    ciating
    0.69
    alore
    0.68
    motion
    0.66
    twitch
    0.64
    Activations Density 0.216%

    No Known Activations