© 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. 6-RES-JB
    11. 12066
    Prev
    Next
    INDEX
    Explanations

    phrases mentioning both sides or multiple entities in a comparison or contrast

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Both" indicating comparisons or contrasts between subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ugu
    -0.82
    uez
    -0.79
    istle
    -0.75
    uable
    -0.75
    agine
    -0.74
    opian
    -0.73
    udic
    -0.72
    plete
    -0.71
    biz
    -0.71
    renheit
    -0.69
    POSITIVE LOGITS
     sexes
    1.33
     halves
    1.30
     sides
    1.25
     genders
    1.11
     parties
    1.05
     sets
    0.87
     kinds
    0.83
     ends
    0.81
     factions
    0.79
     thirds
    0.79
    Activations Density 0.056%

    No Known Activations