© 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. 16040
    Prev
    Next
    INDEX
    Explanations

    parts of a document that contain HTML tags or descriptions of products

    oai_token-act-pair · gpt-3.5-turbo

    specific content descriptors and notable events or 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
    âĢIJ
    -1.70
     ÂŃ
    -1.48
     [âĢ¦]
    -1.37
    ————————
    -1.13
    Advertisements
    -1.03
    âĢ¦
    -1.01
    âĢ³
    -0.95
    ————————————————
    -0.92
    ÂŃ
    -0.92
    âĢ¦]
    -0.92
    POSITIVE LOGITS
     --
    2.56
    --
    1.84
    .--
    1.66
     ----
    1.64
     �
    1.62
     ---
    1.60
    )--
    1.47
     ``
    1.38
    ----
    1.38
    JUST
    1.36
    Activations Density 0.175%

    No Known Activations