© 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. 11-RES-JB
    11. 24418
    Prev
    Next
    INDEX
    Explanations

    emojis and symbols

    oai_token-act-pair · gpt-3.5-turbo

    repeated characters or symbols in text

    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
     princ
    -0.54
     disparate
    -0.49
     coerc
    -0.48
     Truman
    -0.47
     civilisation
    -0.46
     commissions
    -0.45
     marsh
    -0.44
     paternal
    -0.43
     inertia
    -0.43
     masters
    -0.42
    POSITIVE LOGITS
    ª
    0.78
    ľ
    0.77
    ¿
    0.75
    ı
    0.68
    IJ
    0.68
    ¬
    0.67
    ¯
    0.67
    Ĥ
    0.66
    «
    0.65
    ³
    0.65
    Activations Density 0.611%

    No Known Activations