© 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. 10068
    Prev
    Next
    INDEX
    Explanations

    phrases where something is emphasized or highlighted

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "pretty much."

    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
    glass
    -0.68
    odium
    -0.67
    raft
    -0.67
    microsoft
    -0.64
    aline
    -0.63
    yd
    -0.63
    may
    -0.63
    len
    -0.63
    rive
    -0.62
    Tweet
    -0.62
    POSITIVE LOGITS
     everywhere
    1.16
     everything
    1.03
     everyone
    1.02
     everybody
    1.00
     EVERY
    0.94
     nonexistent
    0.94
     every
    0.94
     identical
    0.92
     indistinguishable
    0.90
     anything
    0.90
    Activations Density 0.075%

    No Known Activations