© 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 EvalsExportsinterp-engineNEWAPI 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. 8-RES-JB
    11. 1190
    Prev
    Next
    INDEX
    Explanations

    affiliate links in text

    oai_token-act-pair · gpt-3.5-turbo

    references to affiliate marketing terms and links

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erion
    -0.83
    env
    -0.76
    istically
    -0.75
    obs
    -0.73
    suit
    -0.72
     Escape
    -0.71
    STD
    -0.69
    esa
    -0.68
    sequence
    -0.68
    assetsadobe
    -0.68
    POSITIVE LOGITS
    hips
    0.87
     affiliate
    0.86
    henko
    0.77
     affili
    0.76
     affiliated
    0.74
     recru
    0.74
    iliate
    0.73
     affiliates
    0.71
    iliated
    0.70
     ribbon
    0.69
    Activations Density 0.041%

    No Known Activations