© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 9-RES-JB
    11. 18235
    Prev
    Next
    INDEX
    Explanations

    phrases related to non-profit entities

    oai_token-act-pair · gpt-3.5-turbo

    references to non-profit organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tycoon
    -0.94
     Grind
    -0.71
     Showdown
    -0.69
    IUM
    -0.67
     guts
    -0.66
     Grill
    -0.65
     McGee
    -0.64
     Oaks
    -0.64
     Spoon
    -0.64
     trove
    -0.63
    POSITIVE LOGITS
    chal
    1.33
    linear
    1.29
    etheless
    1.27
    stop
    1.21
    verbal
    1.21
    lethal
    1.21
    profit
    1.14
    compliance
    1.13
    technical
    1.12
    fiction
    1.11
    Activations Density 0.036%

    No Known Activations