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. 20581
    Prev
    Next
    INDEX
    Explanations

    hyperlinks starting with "https" in the text

    oai_token-act-pair · gpt-3.5-turbo

    URLs or hyperlinks

    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
     decre
    -0.68
     ordinarily
    -0.63
     eighty
    -0.63
     twenty
    -0.63
     stubborn
    -0.61
     normally
    -0.61
     acquies
    -0.60
     races
    -0.60
     eject
    -0.59
     persistent
    -0.59
    POSITIVE LOGITS
    https
    4.08
    http
    2.83
     https
    2.43
     http
    1.75
    www
    1.27
    ttp
    1.23
    twitter
    1.21
    youtube
    1.18
    javascript
    1.17
    facebook
    1.17
    Activations Density 0.011%

    No Known Activations