© 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. 10434
    Prev
    Next
    INDEX
    Explanations

    the word **"Att"**

    oai_token-act-pair · gpt-3.5-turbo

    references to a particular individual or group, specifically related to "Attenborough."

    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
    assetsadobe
    -0.95
    çīĪ
    -0.84
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.83
    姫
    -0.81
    theless
    -0.81
    CRIP
    -0.81
    士
    -0.78
     Giuliani
    -0.78
    ktop
    -0.77
    ãģ¦
    -0.75
    POSITIVE LOGITS
    ribute
    1.14
    ributed
    1.11
    anooga
    1.10
    ributes
    1.09
    orneys
    1.02
    ension
    1.02
    itudes
    0.98
    icket
    0.98
    achment
    0.98
    resa
    0.98
    Activations Density 0.005%

    No Known Activations