© 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. 11-RES-JB
    6. 2050
    Prev
    Next
    INDEX
    Explanations

    medical terms related to prosthetics

    oai_token-act-pair · gpt-3.5-turbo

    terms related to medical and technological advancements, especially in prosthetics

    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
    ++++++++++++++++
    -0.68
    footed
    -0.68
    ville
    -0.68
     guiActiveUnfocused
    -0.64
    KER
    -0.63
    ======
    -0.62
    cule
    -0.59
     interstate
    -0.59
     flared
    -0.59
     Coffin
    -0.59
    POSITIVE LOGITS
    nostic
    1.19
    eny
    1.19
    nosis
    1.19
    aming
    1.18
    rame
    0.98
    hetics
    0.97
    ortun
    0.96
    ames
    0.94
    resso
    0.93
    amation
    0.92
    Activations Density 0.068%

    No Known Activations