© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 18365
    Prev
    Next
    INDEX
    Explanations

    words related to vocal abilities or activities

    oai_token-act-pair · gpt-3.5-turbo

    references to vocal expressions or vocalists

    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
    uden
    -0.91
     Reincarn
    -0.91
    agher
    -0.83
    awaru
    -0.78
    roxy
    -0.73
    romeda
    -0.72
     Carbuncle
    -0.69
    ionage
    -0.69
    ģĸ
    -0.68
     Journals
    -0.67
    POSITIVE LOGITS
    izations
    1.26
     cords
    1.20
    isations
    1.17
     chords
    1.06
    izes
    1.00
    izers
    0.99
    izing
    0.98
     fry
    0.95
    ized
    0.94
    izer
    0.92
    Activations Density 0.025%

    No Known Activations