© 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. 1-RES-JB
    11. 20398
    Prev
    Next
    INDEX
    Explanations

    words related to positivity or desirability

    oai_token-act-pair · gpt-3.5-turbo

    words expressing positive or favorable evaluations and opinions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    hid
    -0.88
    grave
    -0.85
    bus
    -0.85
    lang
    -0.82
    liam
    -0.79
    hod
    -0.78
    driver
    -0.75
    jack
    -0.74
    iq
    -0.73
    drivers
    -0.72
    POSITIVE LOGITS
     favorable
    1.40
    avorable
    1.31
     favourable
    1.20
     unfavorable
    1.12
     matchups
    0.97
     favorably
    0.93
     agre
    0.88
     advantageous
    0.86
     favors
    0.85
     ratings
    0.81
    Activations Density 0.007%

    No Known Activations