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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 14351
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Harry"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Harry."

    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
    raints
    -0.70
    PsyNetMessage
    -0.69
    asio
    -0.68
    اÙĦ
    -0.66
    OLOGY
    -0.65
    ocrin
    -0.65
    oute
    -0.64
     commissioner
    -0.64
    alist
    -0.63
     srf
    -0.63
    POSITIVE LOGITS
     Potter
    1.51
     Harry
    1.12
    Harry
    1.03
     Malfoy
    0.91
    haus
    0.85
     Truman
    0.85
    phan
    0.82
     Dresden
    0.82
    awei
    0.80
     Voldemort
    0.78
    Activations Density 0.006%

    No Known Activations