© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 7055
    Prev
    Next
    INDEX
    Explanations

    language related to coding, especially error messaging

    oai_token-act-pair · gpt-3.5-turbo

    instances of punctuation or formatting symbols, indicating potential document boundaries or structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    --------
    -0.31
    Especially
    -0.31
    ÃĥÃĤ
    -0.30
    ¯
    -0.29
    sit
    -0.29
    xxx
    -0.29
    Ó
    -0.29
    nat
    -0.28
    ÃĥÃĤÃĥÃĤ
    -0.28
    ãĥ¼ãĥĨãĤ£
    -0.28
    POSITIVE LOGITS
     Canaver
    0.39
     Xperia
    0.37
     graphene
    0.37
     Rohingya
    0.35
     SpaceX
    0.35
     Houth
    0.34
     OnePlus
    0.34
     Mourinho
    0.33
     Angular
    0.33
     Kejriwal
    0.33
    Activations Density 10.356%

    No Known Activations