© 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. 0-RES-JB
    11. 9701
    Prev
    Next
    INDEX
    Explanations

    keywords related to activism and causes

    oai_token-act-pair · gpt-3.5-turbo

    specific terms associated with charity and social initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     allegedly
    -0.67
     license
    -0.67
     crew
    -0.63
     cut
    -0.63
     scheduled
    -0.61
     mart
    -0.61
     rum
    -0.61
     shots
    -0.60
     GER
    -0.60
     rumored
    -0.60
    POSITIVE LOGITS
    arity
    5.19
    arius
    1.15
    osity
    1.15
    ocity
    1.10
    ality
    1.09
    arian
    1.08
    aries
    1.07
    aires
    1.06
    ARY
    1.03
    ary
    1.00
    Activations Density 0.017%

    No Known Activations