© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 454
    Prev
    Next
    INDEX
    Explanations

    words related to expressing thoughts, opinions, or emotions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "express"

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

    No Comments

    Negative Logits
     Peb
    -0.77
     Skydragon
    -0.75
    quartered
    -0.73
    strap
    -0.72
     Coffin
    -0.71
     Faul
    -0.70
     Beir
    -0.68
     Hungry
    -0.68
     Marino
    -0.67
     Down
    -0.66
    POSITIVE LOGITS
    express
    0.89
     express
    0.86
    ivity
    0.84
    Express
    0.83
    iments
    0.82
    iment
    0.79
    ivities
    0.78
    uron
    0.76
     displeasure
    0.75
    ions
    0.75
    Activations Density 0.015%

    No Known Activations