© 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. 12125
    Prev
    Next
    INDEX
    Explanations

    references to newsletters belonging to a specific entity

    oai_token-act-pair · gpt-3.5-turbo

    references to subscriptions or newsletters

    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
    nesota
    -0.90
    okemon
    -0.77
     Izan
    -0.77
    minster
    -0.73
    wic
    -0.70
    stood
    -0.69
    oldemort
    -0.68
    teness
    -0.68
    ',"
    -0.67
    76561
    -0.65
    POSITIVE LOGITS
    selves
    0.93
     own
    0.93
     newest
    0.87
     exclusive
    0.82
     motto
    0.80
     latest
    0.80
     handy
    0.79
     estimation
    0.76
     inaugural
    0.76
     fearless
    0.75
    Activations Density 0.094%

    No Known Activations