© 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. 20775
    Prev
    Next
    INDEX
    Explanations

    the last names of filmmakers and actors

    oai_token-act-pair · gpt-3.5-turbo

    possessive forms and references to various films and their creators

    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
    hari
    -0.87
    ISO
    -0.79
    aples
    -0.77
    requisites
    -0.74
    AME
    -0.74
    itiz
    -0.73
    teness
    -0.73
    arians
    -0.71
    ophob
    -0.71
    ento
    -0.71
    POSITIVE LOGITS
     seminal
    1.16
     masterpiece
    1.13
     autobiography
    1.03
     newest
    1.01
     bestselling
    1.01
     latest
    0.99
     memoir
    0.96
     debut
    0.96
     Daughter
    0.93
     acclaimed
    0.92
    Activations Density 0.155%

    No Known Activations