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

    Neuronpedia

    Jacobian LensNEW
    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. 2094
    Prev
    Next
    INDEX
    Explanations

    words related to legal actions such as indictments and commandments

    oai_token-act-pair · gpt-3.5-turbo

    terms related to obligations or responsibilities, specifically in the context of commitments and assignments

    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
     pick
    -0.63
     thumb
    -0.61
    OTHER
    -0.59
     killer
    -0.58
     shoot
    -0.56
     assassin
    -0.56
    KN
    -0.56
     shot
    -0.55
     spine
    -0.54
     picking
    -0.53
    POSITIVE LOGITS
    ments
    4.86
    ment
    3.29
    MENTS
    2.77
    mented
    2.51
    MENT
    2.46
    mentation
    2.46
    ements
    1.89
    mental
    1.82
    ement
    1.60
    EMENT
    1.49
    Activations Density 0.012%

    No Known Activations