© 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. 15765
    Prev
    Next
    INDEX
    Explanations

    verbs indicating actions or emotional reactions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating emotions and reactions to change

    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
    selves
    -0.70
     unison
    -0.67
    hub
    -0.63
    they
    -0.57
    angular
    -0.56
    ocument
    -0.55
    VERTISEMENT
    -0.54
     respectively
    -0.54
    taboola
    -0.54
    ADVERTISEMENT
    -0.53
    POSITIVE LOGITS
     himself
    1.80
     Himself
    1.28
     his
    1.25
     herself
    1.11
     HIS
    0.94
     His
    0.92
    his
    0.90
    His
    0.88
     subordinates
    0.79
     wife
    0.70
    Activations Density 2.161%

    No Known Activations