Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 4400
    Prev
    Next
    INDEX
    Explanations

    words with the substring "neighbor"

    oai_token-act-pair · gpt-3.5-turbo

    words that contain the substring "igh"

    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
     ç¥ŀ
    -0.70
     Machina
    -0.70
    ifice
    -0.66
     SPD
    -0.63
    icy
    -0.63
     TAMADRA
    -0.61
     Bubble
    -0.60
     champagne
    -0.59
     ãĤµ
    -0.59
     ANGEL
    -0.59
    POSITIVE LOGITS
    ths
    0.96
    «
    0.94
    bour
    0.93
    awks
    0.92
    awk
    0.91
    bors
    0.90
    orns
    0.89
    teen
    0.87
    terday
    0.86
    mares
    0.85
    Activations Density 0.057%

    No Known Activations