© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 14434
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific company or brand

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word "Build" and its variations in context

    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
    GS
    -0.87
    CLE
    -0.81
     Lizard
    -0.81
    urtle
    -0.81
     gre
    -0.80
     Gle
    -0.78
     Kerr
    -0.76
    hire
    -0.75
    leigh
    -0.74
    glas
    -0.73
    POSITIVE LOGITS
    Ab
    2.23
     Ab
    2.17
     AB
    1.92
    AB
    1.71
    ab
    1.65
     ab
    1.63
     Abram
    1.55
     Abbott
    1.49
     Abby
    1.47
     Abbas
    1.47
    Activations Density 0.251%

    No Known Activations