© 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. 11-RES-JB
    11. 21800
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific names or entities, potentially as part of a larger context

    oai_token-act-pair · gpt-3.5-turbo

    end punctuation and various types of content markers indicating the conclusion of thoughts

    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
     eleph
    -0.53
     hub
    -0.49
     hypot
    -0.49
     displacement
    -0.48
     prud
    -0.46
     habit
    -0.46
     offending
    -0.45
     affected
    -0.45
     contempor
    -0.45
     contingency
    -0.44
    POSITIVE LOGITS
    WASHINGTON
    1.03
    Untitled
    1.01
    Abstract
    1.01
    CLOSE
    1.00
    Description
    0.95
    Overview
    0.92
    Welcome
    0.91
    SAN
    0.91
    LOS
    0.91
    TOR
    0.90
    Activations Density 0.148%

    No Known Activations