© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 11252
    Prev
    Next
    INDEX
    Explanations

    words related to characteristics or qualities

    oai_token-act-pair · gpt-3.5-turbo

    words indicating classifications, characteristics, or specifications of entities

    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
    Ward
    -0.85
    utterstock
    -0.78
    ãĤ¨ãĥ«
    -0.77
    elcome
    -0.76
    inki
    -0.74
    Slot
    -0.74
    anski
    -0.74
    actionDate
    -0.74
    byss
    -0.73
    idelines
    -0.73
    POSITIVE LOGITS
     gorilla
    0.81
     entertainment
    0.78
     affair
    0.73
     tv
    0.70
     english
    0.69
     goodies
    0.68
     radio
    0.68
     approach
    0.67
     FM
    0.66
     americ
    0.66
    Activations Density 0.281%

    No Known Activations