© 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. 9-RES-JB
    11. 2907
    Prev
    Next
    INDEX
    Explanations

    adjectives followed by mention of a person or group receiving praise or criticism

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating assessment or opinion attributed to various groups or individuals

    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
    glass
    -0.73
    hes
    -0.68
    zanne
    -0.68
    chrome
    -0.67
    bender
    -0.64
    interrupted
    -0.64
    hene
    -0.63
    Paper
    -0.62
    bard
    -0.62
    uality
    -0.62
    POSITIVE LOGITS
     pundits
    1.12
     economists
    1.06
     commentators
    1.04
     insiders
    1.02
     critics
    1.01
     policymakers
    1.01
     superiors
    0.99
     outsiders
    0.95
     contemporaries
    0.94
     professionals
    0.94
    Activations Density 0.144%

    No Known Activations