© 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. 21547
    Prev
    Next
    INDEX
    Explanations

    names or terms related to a particular individual

    oai_token-act-pair · gpt-3.5-turbo

    names or references involving individuals, particularly focusing on the variations of "iy" and "y"

    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
     Wilmington
    -0.68
     CONTROL
    -0.64
     Radar
    -0.61
     insol
    -0.60
     Columb
    -0.60
    ULAR
    -0.59
     Inquis
    -0.58
     Hurricanes
    -0.58
     applause
    -0.57
     popcorn
    -0.57
    POSITIVE LOGITS
    adh
    1.18
    arb
    1.18
    ama
    1.14
    ahu
    1.12
    emi
    1.10
    anmar
    1.09
    arag
    1.09
    omi
    1.09
    oga
    1.08
    uan
    1.07
    Activations Density 0.066%

    No Known Activations