© 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. 4-RES-JB
    11. 1059
    Prev
    Next
    INDEX
    Explanations

    words related to cyberspace and cybersecurity

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "bers" referring to various contexts and entities

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

    No Comments

    Negative Logits
     Pont
    -0.77
    asio
    -0.66
    Reviewer
    -0.62
     Bravo
    -0.61
    lihood
    -0.60
    ISON
    -0.57
    UE
    -0.56
    WT
    -0.55
    Bah
    -0.55
    VW
    -0.55
    POSITIVE LOGITS
    hops
    1.21
    pace
    1.18
    erker
    1.14
    paces
    1.12
    mith
    1.09
    uggest
    1.00
    aces
    0.93
    poon
    0.93
    haw
    0.92
    hop
    0.90
    Activations Density 0.012%

    No Known Activations