© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2927
    Prev
    Next
    INDEX
    Explanations

    words related to the name "Mueller."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific names or surnames, particularly those related to people involved in significant events or discussions

    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
    ORN
    -0.72
    ammy
    -0.72
     ILCS
    -0.69
    Weight
    -0.63
    skirts
    -0.62
    ORED
    -0.62
    maxwell
    -0.61
    è£ħ
    -0.60
    District
    -0.60
    Ward
    -0.60
    POSITIVE LOGITS
    vier
    0.94
    lein
    0.89
    ger
    0.85
    gency
    0.79
    raud
    0.77
    pling
    0.75
    pport
    0.75
    iquette
    0.72
    isine
    0.72
    iosity
    0.70
    Activations Density 0.010%

    No Known Activations