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. 2112
    Prev
    Next
    INDEX
    Explanations

    specific mentions of the word 'Skidmore'

    oai_token-act-pair · gpt-3.5-turbo
    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
     writ
    -0.74
     stricken
    -0.68
     sanity
    -0.66
     moot
    -0.66
     sympt
    -0.64
     slee
    -0.64
    âĸ¬âĸ¬
    -0.62
     limited
    -0.60
     normally
    -0.60
     peace
    -0.60
    POSITIVE LOGITS
    yrim
    1.36
    ysc
    1.30
    ipper
    1.26
    ratch
    1.23
    oln
    1.19
    illet
    1.18
    ulpt
    1.18
    illed
    1.17
    irts
    1.16
    rill
    1.15
    Activations Density 0.015%

    No Known Activations