© 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. 4-RES-JB
    11. 14554
    Prev
    Next
    INDEX
    Explanations

    phrases related to dialogue and communication between characters in a written piece

    oai_token-act-pair · gpt-3.5-turbo

    direct speech or conversational dialogue elements

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

    No Comments

    Negative Logits
     denomin
    -0.69
     predominantly
    -0.68
     culminating
    -0.68
    geoning
    -0.67
    CONCLUS
    -0.67
    result
    -0.67
     telev
    -0.65
    uably
    -0.63
    20439
    -0.63
    Attempts
    -0.62
    POSITIVE LOGITS
    -"
    1.12
    —"
    1.04
    âĢ¦"
    0.99
    ..."
    0.98
     âĢ¦"
    0.95
    !?"
    0.93
     Mistress
    0.92
    !"
    0.89
     Mister
    0.88
    ?"
    0.87
    Activations Density 0.525%

    No Known Activations