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. 14639
    Prev
    Next
    INDEX
    Explanations

    decimal numbers

    oai_token-act-pair · gpt-3.5-turbo

    numerical values followed by a decimal point

    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
     newer
    -0.63
     extermination
    -0.63
     tom
    -0.62
     revision
    -0.59
     sometime
    -0.58
     unders
    -0.57
     illegal
    -0.57
     privileged
    -0.57
     travelers
    -0.57
     young
    -0.56
    POSITIVE LOGITS
    005
    1.44
    0001
    1.39
    025
    1.37
    05
    1.34
    001
    1.34
    002
    1.33
    00000
    1.30
    075
    1.26
    004
    1.26
    003
    1.26
    Activations Density 0.042%

    No Known Activations