© 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. 4-RES-JB
    11. 17177
    Prev
    Next
    INDEX
    Explanations

    keywords related to boarding and travel

    oai_token-act-pair · gpt-3.5-turbo

    terms related to boarding and disembarking processes

    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
    icity
    -0.92
    encers
    -0.87
    ifer
    -0.83
    tymology
    -0.79
    lly
    -0.74
    encer
    -0.72
     recession
    -0.71
    vernment
    -0.69
    eanor
    -0.68
    ulkan
    -0.67
    POSITIVE LOGITS
     boarding
    1.23
    walk
    0.95
    folios
    0.91
    wal
    0.90
    boarding
    0.89
    mares
    0.87
    houses
    0.83
    hurst
    0.83
    ĵĺ
    0.83
    rooms
    0.82
    Activations Density 0.010%

    No Known Activations