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. 5882
    Prev
    Next
    INDEX
    Explanations

    the word "oggle" and terms related to numbers

    oai_token-act-pair · gpt-3.5-turbo

    terms related to digital consumption or engagement metrics

    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
    ghai
    -0.69
    Limited
    -0.67
    SourceFile
    -0.67
    aton
    -0.64
    atures
    -0.64
     Grave
    -0.64
     attm
    -0.64
     downed
    -0.64
    ĨĴ
    -0.63
     trapping
    -0.63
    POSITIVE LOGITS
    oggles
    1.82
    oggle
    1.32
    chnology
    0.67
     CASE
    0.66
    esta
    0.65
    aspers
    0.65
    ype
    0.62
     NEO
    0.61
     techn
    0.59
    429
    0.59
    Activations Density 0.003%

    No Known Activations