© 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 EvalsExportsAPI 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. 3-RES-JB
    11. 3680
    Prev
    Next
    INDEX
    Explanations

    words related to specific plans or proposals

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "plan."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Stain
    -0.72
     ILCS
    -0.68
    avery
    -0.67
    omez
    -0.65
    ibaba
    -0.64
    ruciating
    -0.63
    inas
    -0.63
    Chance
    -0.62
     Dam
    -0.61
    ienced
    -0.61
    POSITIVE LOGITS
    isphere
    0.91
     plans
    0.83
    emaker
    0.80
    ters
    0.79
    uary
    0.78
     Plans
    0.77
    plan
    0.76
     2030
    0.76
     plan
    0.74
     outline
    0.74
    Activations Density 0.036%

    No Known Activations