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. 10-RES-JB
    6. 23578
    Prev
    Next
    INDEX
    Explanations

    academic terms and references in research publications

    oai_token-act-pair · gpt-3.5-turbo

    references to academic publishing and peer-reviewed research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Exit
    -0.75
    Connector
    -0.74
     disconnect
    -0.71
    lyak
    -0.68
    irez
    -0.68
    twitch
    -0.67
    served
    -0.65
     refuel
    -0.64
    apego
    -0.64
     thrott
    -0.64
    POSITIVE LOGITS
     journals
    1.81
     newspapers
    1.61
     publications
    1.59
     journal
    1.59
     encyclopedia
    1.57
     magazines
    1.56
     literature
    1.51
     scholarly
    1.44
     textbooks
    1.43
     anthology
    1.42
    Activations Density 0.401%

    No Known Activations