© 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. 2-RES-JB
    11. 3874
    Prev
    Next
    INDEX
    Explanations

    the name "Harold" at varying levels of activation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "Harold."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eanor
    -0.89
    hetically
    -0.83
    psey
    -0.81
    igger
    -0.81
    insula
    -0.80
    ongs
    -0.77
    agogue
    -0.74
    oing
    -0.73
    arnaev
    -0.73
    ocrats
    -0.73
    POSITIVE LOGITS
     Harold
    0.86
     Lank
    0.82
     Kut
    0.80
     McGee
    0.79
     Vaj
    0.77
     Rupert
    0.76
     Melvin
    0.74
    balls
    0.70
     Weinstein
    0.70
     Cald
    0.67
    Activations Density 0.020%

    No Known Activations