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. 7-RES-JB
    6. 820
    Prev
    Next
    INDEX
    Explanations

    conjunctions and prepositions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "but" indicating contrast or contradiction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ery
    -0.78
    gie
    -0.70
    stage
    -0.69
    bit
    -0.63
    rider
    -0.62
    ħĭ
    -0.61
    amus
    -0.60
    grim
    -0.60
    itch
    -0.59
    MI
    -0.59
    POSITIVE LOGITS
     alas
    0.78
     nevertheless
    0.77
     lately
    0.76
     anecd
    0.74
     hindsight
    0.72
    ersen
    0.72
     nonetheless
    0.69
    psons
    0.67
     fortunately
    0.67
     ubiqu
    0.66
    Activations Density 0.242%

    No Known Activations