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. 0-RES-JB
    6. 17155
    Prev
    Next
    INDEX
    Explanations

    mentions of political and financial terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sensitive information and secrets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     inhab
    -0.74
    arc
    -0.73
     pengu
    -0.68
     astroph
    -0.68
     Interstellar
    -0.67
     glac
    -0.67
     avatar
    -0.67
    ark
    -0.67
     interstellar
    -0.65
     galactic
    -0.65
    POSITIVE LOGITS
    icals
    2.45
    rets
    1.94
    tub
    1.78
    wig
    1.47
    gins
    1.31
    imony
    1.20
     tub
    1.20
    nings
    1.14
     Tub
    1.09
    itches
    0.97
    Activations Density 0.038%

    No Known Activations