© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 19417
    Prev
    Next
    INDEX
    Explanations

    conjunctions, particularly the word "and," indicating a connection between different parts of a text

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" as it appears in various contexts

    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
     Riders
    -0.75
     Ki
    -0.73
    wings
    -0.71
     Saiyan
    -0.68
     Survivors
    -0.66
     revisions
    -0.64
     Landing
    -0.64
     Rings
    -0.63
    ADS
    -0.63
    ãĥĩ
    -0.63
    POSITIVE LOGITS
     forcefully
    0.81
     efficiently
    0.80
    iably
    0.80
    ationally
    0.79
     professionally
    0.76
    ilaterally
    0.74
     emphatically
    0.70
     verbally
    0.70
    che
    0.70
     violently
    0.70
    Activations Density 0.207%

    No Known Activations