© 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. 12940
    Prev
    Next
    INDEX
    Explanations

    statements indicating evidence to support arguments or claims

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to evidence and support for claims

    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
    arted
    -0.70
    в
    -0.68
     Fernand
    -0.65
    chn
    -0.65
    lite
    -0.62
    lance
    -0.62
    YY
    -0.59
    loads
    -0.59
     Gazette
    -0.59
     Sophie
    -0.59
    POSITIVE LOGITS
     hypotheses
    1.17
     hypothesis
    1.16
     assertions
    1.07
     assertion
    1.05
     validity
    1.00
     belief
    0.99
     causation
    0.95
     claim
    0.95
     conjecture
    0.95
     proposition
    0.93
    Activations Density 0.290%

    No Known Activations