© 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. 9-RES-JB
    11. 14787
    Prev
    Next
    INDEX
    Explanations

    discussions or references related to the availability or impact of certain items or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to firearms and their implications in society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ij士
    -0.72
    ĺħ
    -0.71
    escription
    -0.69
     Abdel
    -0.66
     Procedure
    -0.63
    RAW
    -0.62
    senal
    -0.62
     Telegram
    -0.62
    everal
    -0.61
    ï¸
    -0.61
    POSITIVE LOGITS
     than
    1.78
    than
    1.39
     Than
    1.22
    efficient
    0.86
     equals
    0.72
    erous
    0.71
     bang
    0.70
    flex
    0.69
     per
    0.67
    worthy
    0.66
    Activations Density 0.367%

    No Known Activations