© 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. 8-RES-JB
    11. 10728
    Prev
    Next
    INDEX
    Explanations

    terms related to production, creation, or generation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "produce" and its variations, indicating a focus on generating or creating outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    laus
    -0.84
    stra
    -0.75
    imb
    -0.75
    pan
    -0.71
    nown
    -0.69
    hai
    -0.68
    uni
    -0.68
    zai
    -0.66
    istani
    -0.66
    hatt
    -0.65
    POSITIVE LOGITS
     offspring
    0.76
    ivity
    0.76
    rious
    0.74
    nces
    0.73
     outputs
    0.73
    Output
    0.69
    encers
    0.69
     batches
    0.68
    ilibrium
    0.68
    idable
    0.66
    Activations Density 0.053%

    No Known Activations