© 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. 3-RES-JB
    11. 23399
    Prev
    Next
    INDEX
    Explanations

    explanations or statements made by individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "explained" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    venge
    -0.77
    emate
    -0.68
    otin
    -0.66
    por
    -0.65
    respective
    -0.65
    eded
    -0.65
    perate
    -0.60
    establishment
    -0.59
    isable
    -0.57
    generated
    -0.57
    POSITIVE LOGITS
     bluntly
    0.79
     sarcast
    0.78
     Cuomo
    0.73
     angrily
    0.70
     omin
    0.68
     emphatically
    0.68
     rhet
    0.67
    WER
    0.66
     aloud
    0.65
     repeatedly
    0.65
    Activations Density 0.259%

    No Known Activations