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. 4023
    Prev
    Next
    INDEX
    Explanations

    the conjunction "And" within sentences

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the word "And" in various contexts

    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
    manship
    -0.70
     WARN
    -0.63
     mound
    -0.59
     nerve
    -0.59
     pall
    -0.59
     vein
    -0.59
     decaying
    -0.58
     chop
    -0.58
     flag
    -0.57
     basement
    -0.56
    POSITIVE LOGITS
    ré
    1.47
    alus
    1.47
    ersen
    1.39
    romeda
    1.38
    hra
    1.37
    rade
    1.37
    ean
    1.28
    rogens
    1.23
    rosc
    1.21
    ross
    1.19
    Activations Density 0.032%

    No Known Activations