© 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 EvalsExportsAPI 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. 3-RES-JB
    11. 20898
    Prev
    Next
    INDEX
    Explanations

    mentions of preference or support towards specific options or individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "favored" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    raz
    -0.79
    sis
    -0.76
    ı
    -0.73
    oufl
    -0.70
    ways
    -0.69
    gaard
    -0.68
    Mar
    -0.68
    Unknown
    -0.66
    urg
    -0.66
    scient
    -0.65
    POSITIVE LOGITS
    itism
    1.39
     favored
    0.94
     favors
    0.92
     favoring
    0.91
     fav
    0.82
     favoured
    0.82
     Fav
    0.81
    iors
    0.75
     disadvant
    0.73
    ited
    0.72
    Activations Density 0.010%

    No Known Activations