© 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. 13013
    Prev
    Next
    INDEX
    Explanations

    references to things outside of a particular context or boundary

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "outside" in relation to environments or experiences

    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
    enegger
    -0.89
    anwhile
    -0.84
    lda
    -0.80
    ruary
    -0.79
    _-
    -0.72
    iji
    -0.72
    dayName
    -0.71
    ony
    -0.68
    amaz
    -0.67
    arrell
    -0.67
    POSITIVE LOGITS
     observer
    0.86
     world
    0.83
     workings
    0.78
    world
    0.76
     linebackers
    0.74
     linebacker
    0.71
     observers
    0.69
     diameter
    0.69
     attractiveness
    0.69
     flap
    0.67
    Activations Density 0.053%

    No Known Activations