© 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. 13088
    Prev
    Next
    INDEX
    Explanations

    phrases related to supporting or endorsing something, such as supporting efforts, artists, the public, an organization, a cause, or an individual

    oai_token-act-pair · gpt-3.5-turbo

    references to support and community efforts

    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
    reflect
    -0.75
    ĸļ
    -0.74
    ftime
    -0.74
    --+
    -0.72
    stem
    -0.70
    hess
    -0.68
    dule
    -0.68
    estyles
    -0.67
     resembles
    -0.67
     resembled
    -0.67
    POSITIVE LOGITS
     fledgling
    1.05
     underdog
    1.03
     nascent
    1.00
     burgeoning
    0.97
     embattled
    0.96
     cause
    0.92
     needy
    0.88
     creation
    0.87
     development
    0.87
     efforts
    0.84
    Activations Density 0.303%

    No Known Activations