© 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. 1-RES-JB
    11. 3428
    Prev
    Next
    INDEX
    Explanations

    specific entities or terms matching the pattern "T number."

    oai_token-act-pair · gpt-3.5-turbo

    the character "T" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.86
    EStream
    -0.79
     actionGroup
    -0.75
    76561
    -0.74
    vernment
    -0.69
     cannabin
    -0.69
     ment
    -0.68
     rounding
    -0.67
    Ĥİ
    -0.66
     Skydragon
    -0.65
    POSITIVE LOGITS
    ARGET
    1.21
    ractor
    1.16
    olkien
    1.16
    TY
    1.09
    ribute
    1.09
    aylor
    1.07
    ribune
    1.07
    ricia
    1.07
    ruck
    1.05
    ravis
    1.04
    Activations Density 0.028%

    No Known Activations