© 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. 3-RES-JB
    11. 18425
    Prev
    Next
    INDEX
    Explanations

    words related to distinctive characteristics or traits

    oai_token-act-pair · gpt-3.5-turbo

    terms related to defining traits or attributes of subjects

    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
    heed
    -0.85
    inth
    -0.82
    ergy
    -0.79
    atorial
    -0.78
    ighth
    -0.77
    ceans
    -0.76
    hens
    -0.73
    apest
    -0.72
    ationally
    -0.71
    Ö¼
    -0.69
    POSITIVE LOGITS
     characteristics
    0.96
     traits
    0.93
    eatures
    0.91
     landmarks
    0.81
     Shape
    0.79
     markings
    0.78
     behaviours
    0.78
     resemb
    0.78
     Patterns
    0.77
     Appearance
    0.77
    Activations Density 0.031%

    No Known Activations