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. 9399
    Prev
    Next
    INDEX
    Explanations

    numerical and statistical data

    oai_token-act-pair · gpt-3.5-turbo

    statistical data and measurements related to social or economic factors

    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
    lear
    -0.71
    lich
    -0.71
     Shroud
    -0.70
     stunt
    -0.69
     dread
    -0.67
     enthusiastic
    -0.67
     signalling
    -0.67
     beck
    -0.66
     sabot
    -0.66
     whispering
    -0.65
    POSITIVE LOGITS
     disag
    1.39
     adjusted
    1.32
     Adjusted
    1.31
    adjusted
    1.30
    verages
    1.24
     weighted
    1.24
     calculates
    1.21
     plotted
    1.21
    chart
    1.20
     calculated
    1.20
    Activations Density 0.684%

    No Known Activations