© 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. 10045
    Prev
    Next
    INDEX
    Explanations

    mention of a specific location, "Back to Gallery"

    oai_token-act-pair · gpt-3.5-turbo

    references to galleries, images, and multimedia content

    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
    ominated
    -0.67
     surviving
    -0.66
    Ħ¢
    -0.64
     scripted
    -0.61
     coinc
    -0.60
     estates
    -0.60
    uced
    -0.60
    oÄŁ
    -0.60
    yth
    -0.59
     fines
    -0.59
    POSITIVE LOGITS
     Submit
    1.12
     »
    1.04
     âĸ
    0.98
    <|endoftext|>
    0.98
     Mehran
    0.94
     [+]
    0.91
     Quote
    0.90
     âĢº
    0.90
     Loading
    0.89
     Ingredients
    0.87
    Activations Density 0.109%

    No Known Activations