© 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 EvalsExportsinterp-engineNEWAPI 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. 1152
    Prev
    Next
    INDEX
    Explanations

    words related to infrastructure and municipal services

    oai_token-act-pair · gpt-3.5-turbo

    contextual references to essential services and their impacts on society

    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
     resemblance
    -0.75
    ieft
    -0.68
     personalities
    -0.67
     adject
    -0.66
     personality
    -0.65
     similarities
    -0.65
     hindsight
    -0.64
     traits
    -0.63
     trolling
    -0.63
     bragging
    -0.63
    POSITIVE LOGITS
     ration
    0.96
     shortages
    0.94
     subsidized
    0.93
    atered
    0.86
     scarce
    0.85
     plentiful
    0.78
    Demand
    0.78
    ©¶æ¥µ
    0.76
     subsid
    0.76
    ufact
    0.75
    Activations Density 0.663%

    No Known Activations