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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 9187
    Prev
    Next
    INDEX
    Explanations

    countries and technology platforms

    oai_token-act-pair · gpt-3.5-turbo

    references to various countries and their relationships or connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ord
    -0.80
    opers
    -0.74
     Defenders
    -0.73
    aling
    -0.72
    leck
    -0.68
    д
    -0.67
    olds
    -0.67
    aqu
    -0.67
    Lenin
    -0.67
    etsk
    -0.67
    POSITIVE LOGITS
     dstg
    0.70
     HDL
    0.69
    illions
    0.68
    YY
    0.67
    ESE
    0.66
    ItemThumbnailImage
    0.65
    aroo
    0.65
    Bron
    0.62
     disorderly
    0.62
    iates
    0.62
    Activations Density 0.264%

    No Known Activations