© 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. 12451
    Prev
    Next
    INDEX
    Explanations

    capitalized words

    oai_token-act-pair · gpt-3.5-turbo

    references to "word" or related concepts 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
    âĹ¼
    -0.73
    DERR
    -0.72
    oute
    -0.64
    ño
    -0.64
    alus
    -0.63
    abama
    -0.63
    ilver
    -0.61
    igure
    -0.59
    oyer
    -0.59
    isner
    -0.59
    POSITIVE LOGITS
    press
    1.41
    sworth
    1.25
     ptr
    0.97
     processor
    0.94
    play
    0.91
    mith
    0.87
    mark
    0.86
     processors
    0.84
     salad
    0.83
    wrap
    0.83
    Activations Density 0.050%

    No Known Activations