© 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. 20818
    Prev
    Next
    INDEX
    Explanations

    specific markers or special characters

    oai_token-act-pair · gpt-3.5-turbo

    indications of chaos or confusion

    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
    ffen
    -0.73
    oft
    -0.71
    imov
    -0.70
    li
    -0.69
    erva
    -0.69
     vic
    -0.69
    ev
    -0.69
    hon
    -0.67
    ther
    -0.67
    orth
    -0.66
    POSITIVE LOGITS
    ilogy
    0.96
    noxious
    0.78
    itars
    0.75
    SPONSORED
    0.72
    itud
    0.70
    izable
    0.68
    ainers
    0.64
    tumblr
    0.64
     cholesterol
    0.64
    é¾
    0.63
    Activations Density 0.000%

    No Known Activations