© 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. 2-RES-JB
    11. 5653
    Prev
    Next
    INDEX
    Explanations

    adjectives related to speed and intensity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "paced" and its variations, indicating a focus on pacing or speed within narratives or descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    roma
    -0.74
    asel
    -0.71
    reditary
    -0.71
     nephew
    -0.70
     pard
    -0.66
    raviolet
    -0.66
    ISS
    -0.64
    ggies
    -0.63
    gur
    -0.62
     discont
    -0.62
    POSITIVE LOGITS
    paced
    1.15
     paced
    1.14
     pacing
    0.94
     pace
    0.88
    ework
    0.86
     Payton
    0.76
     repetition
    0.75
    ographed
    0.72
    aign
    0.72
     rhythms
    0.72
    Activations Density 0.010%

    No Known Activations