© 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. 0-RES-JB
    11. 5247
    Prev
    Next
    INDEX
    Explanations

    verbs related to expressing thoughts, feelings, or opinions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "express" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    killer
    -0.68
    izz
    -0.66
     ner
    -0.63
    ris
    -0.63
     Boom
    -0.61
     Jimmy
    -0.61
    BIP
    -0.61
     Walters
    -0.60
     Setting
    -0.59
     Shots
    -0.59
    POSITIVE LOGITS
     express
    3.85
    express
    2.45
     expresses
    1.96
     Express
    1.90
     expressing
    1.87
    Express
    1.84
     expressed
    1.74
     convey
    1.55
    expression
    1.32
     expressive
    1.28
    Activations Density 0.018%

    No Known Activations