© 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. 20944
    Prev
    Next
    INDEX
    Explanations

    the concept or notion being discussed or explored in the text

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express concepts or notions

    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
    Rated
    -0.60
    ICA
    -0.58
    KO
    -0.56
    dos
    -0.54
    ndum
    -0.54
    zon
    -0.53
    Neg
    -0.53
    ECA
    -0.53
    ilaterally
    -0.52
    Law
    -0.52
    POSITIVE LOGITS
     arises
    1.00
     arose
    0.99
     behind
    0.97
     originated
    0.92
     persists
    0.92
     derives
    0.87
     stems
    0.87
     seems
    0.81
     horr
    0.81
     of
    0.80
    Activations Density 0.148%

    No Known Activations