© 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. 12776
    Prev
    Next
    INDEX
    Explanations

    phrases indicating something comes with a particular consequence or context

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the arrival or introduction of concepts or ideas

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    iffe
    -0.83
    inth
    -0.73
    ²¾
    -0.72
    puters
    -0.71
    neutral
    -0.70
    borough
    -0.70
    Past
    -0.68
    ibi
    -0.68
    chairs
    -0.68
    atform
    -0.67
    POSITIVE LOGITS
     complications
    1.31
     risks
    1.18
     uncertainties
    1.12
     complication
    1.11
     caveats
    1.11
     setbacks
    1.11
     difficulties
    1.10
     pitfalls
    1.09
     complexities
    1.08
     drawbacks
    1.08
    Activations Density 0.284%

    No Known Activations