© 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
    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. 23727
    Prev
    Next
    INDEX
    Explanations

    phrases indicating companionship or togetherness

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "with."

    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
    ouf
    -0.67
    mercial
    -0.62
    ynski
    -0.59
     mislead
    -0.59
    ghai
    -0.58
    pmwiki
    -0.58
     termed
    -0.57
    pton
    -0.56
     normally
    -0.56
    paragraph
    -0.56
    POSITIVE LOGITS
    stood
    1.35
    draw
    1.12
    drawn
    1.11
    standing
    1.01
    holding
    0.97
     impunity
    0.95
     regards
    0.94
     regard
    0.86
     us
    0.83
    held
    0.78
    Activations Density 0.146%

    No Known Activations