© 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. 14250
    Prev
    Next
    INDEX
    Explanations

    words related to names and cultural references with accents or special characters

    oai_token-act-pair · gpt-3.5-turbo

    individual letters or characters in the text

    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
    ãģ®éŃĶ
    -0.65
    fulness
    -0.65
     deprivation
    -0.64
    waves
    -0.60
     coincide
    -0.60
    thro
    -0.57
     starters
    -0.56
    icular
    -0.56
     tackling
    -0.56
    staking
    -0.56
    POSITIVE LOGITS
    ulhu
    1.25
    ugg
    0.92
    arn
    0.90
    ön
    0.90
    unk
    0.89
    Ó
    0.89
    oln
    0.87
    oen
    0.86
    oker
    0.84
    inn
    0.84
    Activations Density 0.163%

    No Known Activations