© 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. 2-RES-JB
    11. 15861
    Prev
    Next
    INDEX
    Explanations

    characteristics or traits that are distinctive or unique in a given context

    oai_token-act-pair · gpt-3.5-turbo

    terms related to characteristics and distinct attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inth
    -0.81
    ceans
    -0.77
    source
    -0.75
    Ö¼
    -0.74
    hens
    -0.73
    apest
    -0.72
    erves
    -0.71
    ML
    -0.70
    ergy
    -0.69
    nih
    -0.69
    POSITIVE LOGITS
    eatures
    0.96
     traits
    0.92
     distinctive
    0.83
    ively
    0.82
     characteristics
    0.82
     trait
    0.78
     arcs
    0.76
     characteristic
    0.76
     qualities
    0.74
     distinguishing
    0.73
    Activations Density 0.010%

    No Known Activations