© 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. 11420
    Prev
    Next
    INDEX
    Explanations

    proper nouns and organizations related to political figures or governmental bodies

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names or terms that include the letter "u" with various diacritical marks, indicating interest in foreign or accented words

    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
    ograp
    -0.96
    ograph
    -0.84
    estate
    -0.83
    ogene
    -0.80
    ographs
    -0.74
    abase
    -0.72
    ographed
    -0.72
     Played
    -0.71
    ographic
    -0.69
    oring
    -0.69
    POSITIVE LOGITS
    ÙĨ
    0.79
    verty
    0.78
    CLASSIFIED
    0.78
    ãĤ©
    0.77
    s
    0.73
    sic
    0.70
    ð
    0.69
    ÄŁ
    0.67
    scribe
    0.67
    Æ
    0.66
    Activations Density 0.070%

    No Known Activations