© 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. 3-RES-JB
    11. 1841
    Prev
    Next
    INDEX
    Explanations

    words related to negative emotions or attitudes such as disillusionment, remorse, irritability, contempt, and distrust

    oai_token-act-pair · gpt-3.5-turbo

    adjectives that describe negative emotional states or disillusionment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oby
    -0.78
    aza
    -0.75
    ufact
    -0.73
    ihilation
    -0.71
    ilater
    -0.70
    ËĪ
    -0.70
    iflower
    -0.69
    estern
    -0.68
    andel
    -0.68
     peanuts
    -0.66
    POSITIVE LOGITS
    soever
    0.78
    ness
    0.69
     pact
    0.69
    uous
    0.67
    */
    0.66
    uously
    0.63
    itus
    0.63
     Celt
    0.62
     Parents
    0.61
     PJ
    0.61
    Activations Density 0.121%

    No Known Activations