© 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. 10-RES-JB
    11. 3118
    Prev
    Next
    INDEX
    Explanations

    names of places or surnames

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Boul" and its variations, likely indicating focus on a specific place or brand

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ENDED
    -0.68
    ãĥ¼ãĥĨãĤ£
    -0.68
    ŀ
    -0.68
     2022
    -0.59
    ITED
    -0.59
    EB
    -0.58
     bye
    -0.57
     buckle
    -0.57
    æĸ¹
    -0.57
    VALUE
    -0.56
    POSITIVE LOGITS
    ouse
    1.08
    ton
    1.01
    otaur
    1.00
    sen
    0.96
    igans
    0.96
    grave
    0.93
    aye
    0.93
    mosp
    0.89
    otine
    0.86
    teenth
    0.86
    Activations Density 0.028%

    No Known Activations