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. 11-RES-JB
    6. 10686
    Prev
    Next
    INDEX
    Explanations

    numerical data mentioned in reports or publications

    oai_token-act-pair · gpt-3.5-turbo

    references to data and reports, particularly about statistics and figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reply
    -0.60
    uces
    -0.60
     dislike
    -0.58
    Mods
    -0.58
    could
    -0.58
     annoy
    -0.57
    instead
    -0.56
     excess
    -0.55
     inconvenience
    -0.55
     beginnings
    -0.54
    POSITIVE LOGITS
     released
    1.28
     compiled
    1.19
     obtained
    1.15
     commissioned
    1.14
     published
    1.10
     reviewed
    1.08
     cited
    1.06
     issued
    1.04
     overseen
    1.02
     supplied
    1.01
    Activations Density 0.136%

    No Known Activations