© 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. 1035
    Prev
    Next
    INDEX
    Explanations

    verbs related to practical skills and activities, particularly focused on teaching and fixing things

    oai_token-act-pair · gpt-3.5-turbo

    topics related to teaching practical skills

    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
     Ars
    -0.56
    !.
    -0.56
     amps
    -0.56
     ."
    -0.56
     Afgh
    -0.55
    $.
    -0.55
    ................................................................
    -0.55
     Puppet
    -0.55
     Ans
    -0.54
     curtains
    -0.54
    POSITIVE LOGITS
    utherford
    0.77
    ithing
    0.74
    iots
    0.70
    inventoryQuantity
    0.70
     accompanies
    0.69
    etitive
    0.69
    rift
    0.68
    ensable
    0.67
    thood
    0.66
     outweigh
    0.63
    Activations Density 1.588%

    No Known Activations