© 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. 10687
    Prev
    Next
    INDEX
    Explanations

    words related to new information or updates

    oai_token-act-pair · gpt-3.5-turbo

    references to news items or reports

    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
    ength
    -0.71
    BuyableInstoreAndOnline
    -0.69
    aughs
    -0.69
    orney
    -0.68
    ause
    -0.66
    struction
    -0.65
    ¯¯
    -0.65
    regor
    -0.64
    inances
    -0.63
    asus
    -0.63
    POSITIVE LOGITS
    worthiness
    1.13
    reader
    1.12
    worthy
    0.99
    agents
    0.92
    room
    0.92
    flash
    0.91
    print
    0.90
    feed
    0.89
    agent
    0.85
    letter
    0.84
    Activations Density 0.035%

    No Known Activations