© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 9-RES-JB
    11. 10243
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific organizations or entities

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the existence of organizations or systems

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Caller
    -0.67
    iddler
    -0.64
     Checking
    -0.63
    Mech
    -0.63
    isher
    -0.60
     additional
    -0.59
     Landing
    -0.58
     Metatron
    -0.58
     docking
    -0.57
     clearing
    -0.56
    POSITIVE LOGITS
     celebrates
    0.94
     resembles
    0.91
     thri
    0.89
     wors
    0.88
     lacks
    0.88
     embodies
    0.85
     spans
    0.83
     loves
    0.82
     encompasses
    0.82
     horr
    0.81
    Activations Density 0.167%

    No Known Activations