© 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. 1-RES-JB
    11. 14028
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Mevinsky" in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Mezvinsky."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ¼ãĥ³
    -0.76
    chal
    -0.66
    origin
    -0.65
    worldly
    -0.65
    mostly
    -0.62
    ileen
    -0.60
    atively
    -0.60
    venge
    -0.59
    ibal
    -0.59
    orial
    -0.58
    POSITIVE LOGITS
    insky
    1.37
    issance
    0.94
    zinski
    0.94
    loo
    0.85
    ihilation
    0.78
    aunders
    0.76
    isi
    0.76
    baum
    0.75
    inski
    0.73
    ratulations
    0.73
    Activations Density 0.009%

    No Known Activations