© 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. 20880
    Prev
    Next
    INDEX
    Explanations

    references to productions or works that have gained significant popularity or recognition

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "has" in various contexts

    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
    lex
    -0.69
     trusts
    -0.64
     Framework
    -0.63
     Monitor
    -0.63
     Corpus
    -0.62
    doms
    -0.61
    Distance
    -0.60
    inance
    -0.60
     Consider
    -0.60
     Exercise
    -0.59
    POSITIVE LOGITS
     garnered
    1.27
     been
    1.23
     become
    1.16
     undergone
    1.15
     surfaced
    1.12
     gotten
    1.10
     risen
    1.08
     spawned
    1.06
    been
    1.06
     morphed
    1.04
    Activations Density 0.143%

    No Known Activations