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. 2-RES-JB
    6. 20442
    Prev
    Next
    INDEX
    Explanations

    instances where assistance or help is requested or offered

    oai_token-act-pair · gpt-3.5-turbo

    requests for assistance or support in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ctica
    -0.87
    asio
    -0.78
    Downloadha
    -0.77
     deaf
    -0.75
    ocobo
    -0.71
    USE
    -0.69
    livion
    -0.68
    ounter
    -0.67
    querade
    -0.67
     reper
    -0.66
    POSITIVE LOGITS
    ing
    1.73
    ed
    1.21
    edIn
    1.10
    ingham
    1.06
    ership
    0.99
    edin
    0.98
    ington
    0.98
     Contracts
    0.84
    eous
    0.82
    edly
    0.82
    Activations Density 0.112%

    No Known Activations