© 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. 9-RES-JB
    11. 11196
    Prev
    Next
    INDEX
    Explanations

    verbs related to difficulty or complexity in comprehension or execution

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to difficulty and complexity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Parables
    -0.63
    agons
    -0.61
    psey
    -0.60
     teasp
    -0.60
    letters
    -0.60
     Herrera
    -0.59
    bon
    -0.58
    é£
    -0.57
    889
    -0.57
     Said
    -0.57
    POSITIVE LOGITS
     oneself
    0.96
     nowadays
    0.84
     unless
    0.79
    due
    0.78
     accurately
    0.72
     reliably
    0.72
     anyway
    0.71
     navigate
    0.70
     anyways
    0.70
    istically
    0.70
    Activations Density 0.187%

    No Known Activations