© 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. 24202
    Prev
    Next
    INDEX
    Explanations

    verbs indicating an action or event taking place

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to events occurring at specific times

    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
    ateg
    -0.70
    mini
    -0.66
    luaj
    -0.65
     Trees
    -0.63
    holm
    -0.63
    BIP
    -0.62
    croft
    -0.62
    tx
    -0.61
    idding
    -0.59
    patrick
    -0.58
    POSITIVE LOGITS
     place
    1.23
     precedence
    1.22
     advantage
    0.98
    aways
    0.94
     care
    0.92
    place
    0.90
     effect
    0.80
    places
    0.79
     awhile
    0.76
     pains
    0.76
    Activations Density 0.060%

    No Known Activations