© 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. 8-RES-JB
    11. 2350
    Prev
    Next
    INDEX
    Explanations

    adjectives indicating a sense of seriousness or danger

    oai_token-act-pair · gpt-3.5-turbo

    words related to grimness and dire circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ertodd
    -0.85
    adesh
    -0.75
    blance
    -0.68
     actionGroup
    -0.67
    APS
    -0.67
    afort
    -0.66
     enzyme
    -0.64
    rase
    -0.63
    ãħĭ
    -0.63
     includ
    -0.60
    POSITIVE LOGITS
    oire
    1.16
    ace
    1.05
    ly
    1.00
    grim
    0.92
     outlook
    0.92
    dark
    0.91
    acing
    0.90
    aces
    0.89
     prog
    0.89
    wolf
    0.83
    Activations Density 0.070%

    No Known Activations