© 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. 13437
    Prev
    Next
    INDEX
    Explanations

    negative adjectives related to intelligence or decision-making

    oai_token-act-pair · gpt-3.5-turbo

    terms related to intelligence and foolishness

    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
    ophon
    -0.66
     artif
    -0.66
     sclerosis
    -0.62
     convergence
    -0.62
    ANGE
    -0.59
     unden
    -0.58
     heterogeneity
    -0.58
    ample
    -0.56
     inverse
    -0.55
    irie
    -0.54
    POSITIVE LOGITS
     to
    1.13
    to
    0.95
     TO
    0.87
    To
    0.83
     To
    0.82
     financially
    0.72
     ta
    0.72
     whatsoever
    0.69
     anymore
    0.69
     emotionally
    0.68
    Activations Density 0.267%

    No Known Activations