© 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. 2-RES-JB
    11. 20971
    Prev
    Next
    INDEX
    Explanations

    speeches or instances of public speaking

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Speaking" followed by context related to discussions or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    76561
    -0.85
    ifle
    -0.77
    ãĥĩãĤ£
    -0.77
    jer
    -0.74
    aden
    -0.73
    urses
    -0.66
    berus
    -0.66
    ascade
    -0.66
    peg
    -0.66
    strip
    -0.65
    POSITIVE LOGITS
     aloud
    1.06
    Speaking
    0.92
     Speaking
    0.89
    Laughs
    0.77
     volumes
    0.76
    voice
    0.75
    ophone
    0.74
     fluent
    0.74
     Loud
    0.73
    ness
    0.72
    Activations Density 0.008%

    No Known Activations