© 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 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. 9
    Prev
    Next
    INDEX
    Explanations

    contractions paired with the verb 'to be'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "I'm" or similar self-referential statements

    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
    ainer
    -0.66
     separates
    -0.66
     looms
    -0.65
     mater
    -0.65
     perish
    -0.64
     Tactics
    -0.64
     Reduce
    -0.62
     Gad
    -0.62
     Stim
    -0.62
     Deter
    -0.61
    POSITIVE LOGITS
     gonna
    1.29
     glad
    0.95
     going
    0.90
     gotta
    0.89
     thankful
    0.88
     lucky
    0.86
     hoping
    0.86
     fortunate
    0.84
     afraid
    0.83
     not
    0.82
    Activations Density 0.039%

    No Known Activations