© 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. 24240
    Prev
    Next
    INDEX
    Explanations

    specific numbers related to quantity or measurement

    oai_token-act-pair · gpt-3.5-turbo

    references to geographic locations and related statistical data

    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
    ollah
    -0.65
    soType
    -0.65
    politics
    -0.61
    Assembly
    -0.60
    grass
    -0.59
    ——
    -0.57
    .}
    -0.57
    undy
    -0.56
    ught
    -0.56
    URR
    -0.56
    POSITIVE LOGITS
     famously
    1.05
    ahime
    0.81
     langu
    0.77
     likewise
    0.75
     prominently
    0.72
     egreg
    0.69
    vertisement
    0.66
     similarly
    0.65
     unilaterally
    0.65
     recently
    0.65
    Activations Density 0.886%

    No Known Activations