© 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. 9486
    Prev
    Next
    INDEX
    Explanations

    the word "need" followed by various contexts and scenarios in which a need is expressed

    oai_token-act-pair · gpt-3.5-turbo

    calls to action emphasizing the necessity for various societal changes or improvements

    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
    anka
    -0.66
    dylib
    -0.63
     quir
    -0.61
    ipop
    -0.61
    gdala
    -0.60
    cheat
    -0.60
    creen
    -0.58
    luaj
    -0.58
     Trailer
    -0.57
    bourne
    -0.54
    POSITIVE LOGITS
    lessly
    1.20
    n
    0.81
    nces
    0.81
    HAEL
    0.75
    END
    0.72
    enegger
    0.71
    ILY
    0.71
    ORTS
    0.70
    rils
    0.68
    onies
    0.67
    Activations Density 0.066%

    No Known Activations