© 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. 9-RES-JB
    11. 10064
    Prev
    Next
    INDEX
    Explanations

    specific names or terms

    oai_token-act-pair · gpt-3.5-turbo

    specific names and terms associated with entities or concepts in a given context

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Advoc
    -0.83
     prost
    -0.80
     ATT
    -0.75
     advoc
    -0.73
     Akira
    -0.73
     Dynam
    -0.72
     sacks
    -0.72
     Oscars
    -0.72
     ADV
    -0.72
     ISS
    -0.72
    POSITIVE LOGITS
    ne
    1.29
    te
    1.23
    me
    1.16
    ple
    1.07
    ffe
    1.05
    pine
    1.05
    le
    1.02
    mes
    1.02
    ten
    1.00
    onse
    0.97
    Activations Density 0.294%

    No Known Activations