© 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. 0-RES-JB
    11. 11969
    Prev
    Next
    INDEX
    Explanations

    terms related to discussions or conversations on various topics

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "discourse" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    STAR
    -0.67
    uin
    -0.67
    min
    -0.65
     Miner
    -0.63
     Ow
    -0.63
     Merrill
    -0.63
    ump
    -0.61
    Size
    -0.61
     Olsen
    -0.61
     Boss
    -0.60
    POSITIVE LOGITS
     discourse
    3.51
     conversation
    1.61
     rhetoric
    1.54
     discussion
    1.53
     debate
    1.53
     dialogue
    1.51
     debates
    1.40
     Debate
    1.39
     vocabulary
    1.32
     narrative
    1.28
    Activations Density 0.011%

    No Known Activations