© 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. 369
    Prev
    Next
    INDEX
    Explanations

    phrases related to giving speeches or addresses

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the giving of speeches or addresses

    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
    zu
    -0.83
    estine
    -0.73
    Prev
    -0.72
    acci
    -0.65
    ahime
    -0.63
    vant
    -0.62
    runs
    -0.61
    âĿ
    -0.61
    âĻ¥
    -0.61
    van
    -0.61
    POSITIVE LOGITS
     attendees
    1.19
     reporters
    1.18
     audiences
    1.16
     delegates
    1.13
     constituents
    1.09
     shareholders
    1.09
     listeners
    1.07
     supporters
    1.04
     graduating
    1.04
     students
    1.03
    Activations Density 0.147%

    No Known Activations