© 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. 23089
    Prev
    Next
    INDEX
    Explanations

    phrases related to educating others

    oai_token-act-pair · gpt-3.5-turbo

    terms related to education and awareness

    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
    imposed
    -0.64
    ãĤ´ãĥ³
    -0.62
     deduction
    -0.60
    lived
    -0.59
     LIMITED
    -0.58
     fav
    -0.57
    nothing
    -0.56
    dates
    -0.56
    issues
    -0.56
    offer
    -0.56
    POSITIVE LOGITS
     youngsters
    0.98
     people
    0.98
     them
    0.92
     readers
    0.90
     listeners
    0.90
     passers
    0.89
     others
    0.89
     viewers
    0.89
     audiences
    0.89
     unsuspecting
    0.87
    Activations Density 0.261%

    No Known Activations