© 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. 7-RES-JB
    11. 21160
    Prev
    Next
    INDEX
    Explanations

    phrases related to early stages or assessments

    oai_token-act-pair · gpt-3.5-turbo

    content related to early assessment or uncertain outcomes

    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
    aunts
    -0.70
     knack
    -0.70
    ails
    -0.68
    oward
    -0.65
     drives
    -0.63
     baskets
    -0.62
     manif
    -0.62
     sack
    -0.62
    choice
    -0.61
    iesta
    -0.60
    POSITIVE LOGITS
     copyrighted
    0.84
     spoilers
    0.82
     unpublished
    0.82
     strictly
    0.82
     Attribution
    0.80
    Disclaimer
    0.80
     confidential
    0.78
     anonym
    0.77
     confidentiality
    0.77
     ONLY
    0.75
    Activations Density 1.048%

    No Known Activations