© 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. 9-RES-JB
    11. 15896
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "a" followed by a proper noun

    oai_token-act-pair · gpt-3.5-turbo

    articles and nouns that begin with the letter "a"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Versions
    -0.84
    APD
    -0.83
    ['
    -0.82
    daq
    -0.80
    Alien
    -0.79
    EMA
    -0.79
    Aim
    -0.75
    xd
    -0.74
    Īè
    -0.74
    DragonMagazine
    -0.73
    POSITIVE LOGITS
     powerful
    1.02
     versatile
    1.00
     wonderful
    0.99
     unique
    0.98
     fantastic
    0.97
     recurring
    0.96
     fascinating
    0.94
     fictional
    0.94
     terrific
    0.93
     wonderfully
    0.92
    Activations Density 0.120%

    No Known Activations