© 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. 20131
    Prev
    Next
    INDEX
    Explanations

    phrases related to presenting a list of points or items

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "there are."

    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
    hood
    -0.70
    ð
    -0.67
    udeau
    -0.67
    speak
    -0.65
    gypt
    -0.63
    wake
    -0.63
    oting
    -0.62
    town
    -0.61
    adesh
    -0.60
     topple
    -0.60
    POSITIVE LOGITS
    wolves
    0.95
    女
    0.90
     plenty
    0.82
     hereby
    0.81
     occasions
    0.78
     similarities
    0.75
     gonna
    0.74
     indications
    0.74
     exceptions
    0.73
    nt
    0.72
    Activations Density 0.077%

    No Known Activations