© 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. 4-RES-JB
    11. 1249
    Prev
    Next
    INDEX
    Explanations

    words related to an individual's last name or surname

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "ard" or related name constructs

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

    No Comments

    Negative Logits
    ĸļ
    -0.97
    pheus
    -0.86
    PER
    -0.81
    psey
    -0.74
    phis
    -0.72
    ĺħ
    -0.71
    igslist
    -0.70
    uyomi
    -0.69
     amen
    -0.65
    PROV
    -0.65
    POSITIVE LOGITS
    ragon
    0.90
    ice
    0.90
     Mechdragon
    0.88
    furt
    0.87
    ard
    0.83
    aign
    0.83
    rill
    0.82
    ness
    0.82
    inas
    0.81
    rums
    0.81
    Activations Density 0.016%

    No Known Activations