© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11322
    Prev
    Next
    INDEX
    Explanations

    positive and negative evaluations emphasizing contrast and comparison

    oai_token-act-pair · gpt-3.5-turbo

    contradictory statements or contrasting phrases in evaluations or reviews

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

    No Comments

    Negative Logits
    reen
    -0.74
    dayName
    -0.73
    éĹĺ
    -0.73
    nan
    -0.72
    llah
    -0.72
    successfully
    -0.72
    vance
    -0.70
    shore
    -0.70
    itched
    -0.68
    si
    -0.66
    POSITIVE LOGITS
     beware
    1.07
     alas
    1.02
     unfortunately
    1.02
     downside
    0.90
     hindered
    0.88
     drawbacks
    0.87
     sadly
    0.81
     hampered
    0.81
     pitfalls
    0.81
     compromises
    0.80
    Activations Density 0.357%

    No Known Activations