© 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. 6-RES-JB
    11. 9539
    Prev
    Next
    INDEX
    Explanations

    words containing special characters like ÂŃ

    oai_token-act-pair · gpt-3.5-turbo

    indications of large quantities or abundance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     intimidated
    -0.63
     Nebula
    -0.61
    DragonMagazine
    -0.60
     Spice
    -0.60
    ilts
    -0.60
     Skull
    -0.60
     remake
    -0.59
    engeance
    -0.58
     Hats
    -0.58
     Kore
    -0.57
    POSITIVE LOGITS
    ships
    0.81
    selves
    0.81
    ship
    0.78
    tal
    0.77
    la
    0.75
    nesota
    0.73
    city
    0.72
    Ñı
    0.71
    late
    0.69
    tion
    0.69
    Activations Density 0.018%

    No Known Activations