© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 8-RES-JB
    11. 13075
    Prev
    Next
    INDEX
    Explanations

    numerical values associated with instructions or steps

    oai_token-act-pair · gpt-3.5-turbo

    phrases that suggest imagination or perception from the reader's perspective

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    kefeller
    -0.71
    imer
    -0.71
    bage
    -0.64
    alloc
    -0.64
    anqu
    -0.62
    pan
    -0.61
     Ambro
    -0.61
    endas
    -0.60
    igmat
    -0.58
    heres
    -0.57
    POSITIVE LOGITS
     guessed
    0.78
    Know
    0.73
    ees
    0.69
     wont
    0.64
    Lear
    0.63
    ee
    0.63
     notice
    0.61
    ħĭ
    0.60
    Reviewer
    0.60
     sensing
    0.60
    Activations Density 0.070%

    No Known Activations