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. 11-RES-JB
    6. 19859
    Prev
    Next
    INDEX
    Explanations

    the word 'And' at different positions in sentences

    oai_token-act-pair · gpt-3.5-turbo

    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 @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     downhill
    -0.59
     nerve
    -0.58
     mound
    -0.57
     spot
    -0.57
    manship
    -0.57
     basement
    -0.56
     vac
    -0.55
     PAGE
    -0.55
     tip
    -0.55
     flag
    -0.55
    POSITIVE LOGITS
    alus
    1.59
    ré
    1.51
    rade
    1.49
    ean
    1.37
    ersen
    1.35
    rosc
    1.33
    romeda
    1.31
    hra
    1.31
    rus
    1.30
    orians
    1.27
    Activations Density 0.044%

    No Known Activations