© 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. 0-RES-JB
    11. 2492
    Prev
    Next
    INDEX
    Explanations

    words related to frozen conditions or terms like "factory" and "factory mechanisms"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to frozen or cold environments and associated concepts like frost and freezing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dwar
    -0.74
     dwarf
    -0.70
     guard
    -0.70
     denial
    -0.69
     NV
    -0.67
     Hulk
    -0.67
     Piece
    -0.66
     hell
    -0.66
     fut
    -0.65
     fals
    -0.65
    POSITIVE LOGITS
    actory
    2.11
    rozen
    2.02
    rost
    1.99
    amiliar
    1.92
    ruit
    1.83
    ellow
    1.82
    estival
    1.78
    ranch
    1.74
    riend
    1.71
    lux
    1.67
    Activations Density 0.043%

    No Known Activations