© 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. 22002
    Prev
    Next
    INDEX
    Explanations

    references to historical figures and events

    oai_token-act-pair · gpt-3.5-turbo

    names and titles of historical monarchs

    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
    GAN
    -0.78
    Room
    -0.74
    ties
    -0.71
    Consumer
    -0.71
    details
    -0.70
    malink
    -0.70
    Member
    -0.68
    Parts
    -0.67
     locker
    -0.67
    GREEN
    -0.66
    POSITIVE LOGITS
     XIV
    1.32
     VIII
    1.31
     VII
    1.30
     XIII
    1.27
     Augustus
    1.23
     XII
    1.20
     ibn
    1.17
     XVI
    1.16
     XV
    1.13
     VI
    1.11
    Activations Density 0.223%

    No Known Activations