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. 4-RES-JB
    6. 19282
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to disconnection or detachment

    oai_token-act-pair · gpt-3.5-turbo

    terms related to social connections and disconnections

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

    No Comments

    Negative Logits
    gg
    -0.71
    gio
    -0.70
    GB
    -0.67
    Rub
    -0.66
    OPER
    -0.66
    TRY
    -0.63
    esan
    -0.62
    DOM
    -0.61
    ggle
    -0.60
     enforce
    -0.60
    POSITIVE LOGITS
     disconnect
    1.04
    icut
    0.88
    owship
    0.85
    connection
    0.78
    nect
    0.75
     disconnected
    0.75
    racted
    0.74
    aline
    0.73
    yip
    0.72
    chart
    0.72
    Activations Density 0.013%

    No Known Activations