© 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. 2807
    Prev
    Next
    INDEX
    Explanations

    direct quotes and reported speech

    oai_token-act-pair · gpt-3.5-turbo

    discourses related to interviews and statements made by individuals

    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
     vec
    -0.96
    vec
    -0.88
     Tucson
    -0.88
     filament
    -0.78
     resil
    -0.76
    acco
    -0.75
     FTP
    -0.73
    yout
    -0.72
     Scully
    -0.72
     contam
    -0.72
    POSITIVE LOGITS
    King
    2.29
     King
    2.23
     KING
    1.91
     monarch
    1.90
     king
    1.83
     Kingdom
    1.82
     monarchy
    1.78
     kingdom
    1.77
     Kings
    1.76
     royal
    1.73
    Activations Density 0.328%

    No Known Activations