© 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. 11202
    Prev
    Next
    INDEX
    Explanations

    words related to direct addressing or instruction to the reader

    oai_token-act-pair · gpt-3.5-turbo

    the recurring use of the word "you" along with phrases that imply expectations or experiences

    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
    Reloaded
    -0.67
    ensable
    -0.61
     resumes
    -0.59
    Champ
    -0.58
    ween
    -0.57
     intens
    -0.56
     srfAttach
    -0.54
    yss
    -0.54
    wrapper
    -0.53
    otom
    -0.53
    POSITIVE LOGITS
    'll
    1.29
    'd
    1.09
    're
    1.05
     might
    1.02
     see
    1.00
    've
    0.98
     hear
    0.96
    tub
    0.92
    kai
    0.88
     guessed
    0.87
    Activations Density 0.124%

    No Known Activations