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. 8463
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Jeh" in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Jeopardy" and its variations

    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
    raviolet
    -0.79
    ancial
    -0.76
    IUM
    -0.75
     Anthem
    -0.73
    ãĥ¼ãĥĨ
    -0.70
    oresc
    -0.66
    ificantly
    -0.66
    imately
    -0.66
    IAL
    -0.65
     rooting
    -0.64
    POSITIVE LOGITS
    opard
    1.21
    zeb
    1.00
    hovah
    0.94
     Je
    0.90
    Je
    0.90
    anty
    0.89
    pee
    0.87
    apons
    0.86
    efe
    0.83
    Maker
    0.83
    Activations Density 0.005%

    No Known Activations