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. 4506
    Prev
    Next
    INDEX
    Explanations

    references to software application programming interfaces (APIs)

    oai_token-act-pair · gpt-3.5-turbo

    references to APIs in various contexts

    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
    Ń·
    -0.70
     gloom
    -0.69
     airs
    -0.67
    ength
    -0.63
    mort
    -0.62
     stricken
    -0.62
     bunk
    -0.62
    thur
    -0.61
    aden
    -0.61
    egal
    -0.61
    POSITIVE LOGITS
     API
    3.41
     APIs
    2.74
    API
    2.58
     api
    2.40
    api
    1.97
     SDK
    1.83
     REST
    1.37
     RPC
    1.35
     interface
    1.31
     HTTP
    1.28
    Activations Density 0.025%

    No Known Activations