© 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. 10-RES-JB
    11. 3044
    Prev
    Next
    INDEX
    Explanations

    items or events related to behind-the-scenes activities

    oai_token-act-pair · gpt-3.5-turbo

    references to behind-the-scenes content or footage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ickle
    -0.83
    ipolar
    -0.80
    asonable
    -0.72
    sole
    -0.71
    cffff
    -0.70
    gres
    -0.69
    erenn
    -0.69
    abet
    -0.67
    Boost
    -0.66
    immune
    -0.65
    POSITIVE LOGITS
     footage
    1.88
     photos
    1.57
     photographs
    1.54
     pictures
    1.50
     photograph
    1.47
     images
    1.46
     pics
    1.43
     photo
    1.39
     glimpse
    1.36
     video
    1.36
    Activations Density 0.530%

    No Known Activations