© 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. 0-RES-JB
    11. 8291
    Prev
    Next
    INDEX
    Explanations

    phrases related to architectural structures

    oai_token-act-pair · gpt-3.5-turbo

    terms related to structures or concepts associated with "arch."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mAh
    -0.69
     Marketable
    -0.69
    Tesla
    -0.68
    eering
    -0.68
    Comb
    -0.67
    igun
    -0.67
    Veh
    -0.66
    rained
    -0.65
     Nissan
    -0.64
    Pos
    -0.64
    POSITIVE LOGITS
     arch
    4.07
     Arch
    2.34
    Arch
    1.87
    arch
    1.38
     archive
    1.38
     archives
    1.31
     Archbishop
    1.30
     Archive
    1.17
     Archives
    1.13
     arche
    1.11
    Activations Density 0.010%

    No Known Activations