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. 17651
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names of persons

    oai_token-act-pair · gpt-3.5-turbo

    specific identifiers or references to monetary values and distinct items

    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
    SC
    -0.91
     Sev
    -0.86
     Sparks
    -0.85
     Space
    -0.84
    к
    -0.81
     Suc
    -0.81
     Tsuk
    -0.80
    solid
    -0.80
     Spur
    -0.79
    Solid
    -0.78
    POSITIVE LOGITS
     34
    0.90
    ami
    0.83
    onso
    0.83
    34
    0.82
    341
    0.82
     341
    0.81
     356
    0.78
    oni
    0.78
     Alonso
    0.77
    ania
    0.76
    Activations Density 0.377%

    No Known Activations