© 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. 0-RES-JB
    11. 16659
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific term related to "Prism" or similar keywords with associated numbers

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Prism" and associated contexts related to surveillance or monitoring

    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
     Corker
    -0.75
     sounding
    -0.73
     whiff
    -0.69
     credibility
    -0.67
     Katy
    -0.66
     Burnett
    -0.65
     bite
    -0.65
     muff
    -0.64
     endorsement
    -0.64
     wreck
    -0.64
    POSITIVE LOGITS
    Pr
    4.01
     Pr
    2.06
    pr
    1.82
    Ru
    1.43
     pr
    1.29
    Pri
    1.28
    Pi
    1.22
     Prism
    1.20
     Prison
    1.17
    PR
    1.13
    Activations Density 0.009%

    No Known Activations