© 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. 6-RES-JB
    11. 12082
    Prev
    Next
    INDEX
    Explanations

    statements related to legal or criminal activities, specifically focusing on individuals or actions

    oai_token-act-pair · gpt-3.5-turbo

    important individuals or roles in a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     conver
    -0.69
     converge
    -0.64
     equivalent
    -0.64
     respectively
    -0.63
    ideon
    -0.63
     common
    -0.63
    iosyncr
    -0.62
     societies
    -0.61
    orns
    -0.60
     collective
    -0.60
    POSITIVE LOGITS
    âĹ¼
    0.76
    henko
    0.74
    tesy
    0.71
     Targ
    0.68
    bilt
    0.67
     personally
    0.67
    Film
    0.66
     himself
    0.65
    enegger
    0.64
    Care
    0.63
    Activations Density 0.443%

    No Known Activations