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. 1440
    Prev
    Next
    INDEX
    Explanations

    Twitter handles and website URLs

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations or acronyms often related to digital media or technology contexts

    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
    ATIVE
    -0.83
     LIFE
    -0.77
    FUL
    -0.73
    IZE
    -0.70
     CONTROL
    -0.68
     afore
    -0.68
    ALLY
    -0.67
     Zed
    -0.67
    GROUND
    -0.64
     SHE
    -0.64
    POSITIVE LOGITS
    cs
    1.09
    cc
    1.01
    gs
    0.97
    fp
    0.97
    fs
    0.97
    cb
    0.96
    ctr
    0.95
    RN
    0.95
    cd
    0.95
    pd
    0.94
    Activations Density 0.135%

    No Known Activations