© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 6554
    Prev
    Next
    INDEX
    Explanations

    descriptions related to physical attributes and spatial relationships

    oai_token-act-pair · gpt-3.5-turbo

    descriptive phrases related to physical attributes or states of objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ivals
    -0.82
    rities
    -0.81
    =-=-=-=-
    -0.78
     Calls
    -0.76
     Promotion
    -0.76
     titles
    -0.75
     Income
    -0.73
     Criminal
    -0.71
    ativity
    -0.71
     Debate
    -0.69
    POSITIVE LOGITS
     thicker
    1.36
     coated
    1.31
     thinner
    1.29
     translucent
    1.25
     curved
    1.23
     adorned
    1.19
     porous
    1.17
     protr
    1.16
     stained
    1.14
     brittle
    1.12
    Activations Density 0.277%

    No Known Activations