© 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 EvalsExportsinterp-engineNEWAPI 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. 16428
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a majority or a prominent portion

    oai_token-act-pair · gpt-3.5-turbo

    phrases that start with "most of."

    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
     Cosponsors
    -0.79
    ĸļ
    -0.73
    resy
    -0.70
    CHAT
    -0.68
    İĭ
    -0.67
     Samson
    -0.64
    ħĭ
    -0.63
    gee
    -0.63
     sizing
    -0.62
     Delete
    -0.62
    POSITIVE LOGITS
     imaginable
    0.89
    icial
    0.81
     course
    0.80
    course
    0.71
    amina
    0.68
     ours
    0.63
    olar
    0.62
    ocate
    0.61
    odor
    0.59
    icult
    0.59
    Activations Density 0.131%

    No Known Activations