© 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. 3-RES-JB
    11. 5528
    Prev
    Next
    INDEX
    Explanations

    capital letters followed by numbers

    oai_token-act-pair · gpt-3.5-turbo

    the capital letter "L"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĹĺ
    -0.78
    smanship
    -0.72
    ãĥ¼ãĤ¯
    -0.70
    ij士
    -0.66
     Subtle
    -0.65
    é¾įå¥ij士
    -0.64
    ãĥ¼ãĥĨãĤ£
    -0.63
    ãĥĹ
    -0.63
     Primal
    -0.61
    ħĭ
    -0.61
    POSITIVE LOGITS
    azy
    1.17
    yrics
    1.14
    ocker
    1.10
    adders
    1.09
    ateral
    1.08
    aughter
    1.05
    oyd
    1.04
    isted
    1.03
    IGHT
    1.02
    ifestyle
    1.02
    Activations Density 0.039%

    No Known Activations