© 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. 23285
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Wizard"

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "wizard."

    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
    uters
    -0.82
    ¿½
    -0.75
    give
    -0.74
    PER
    -0.72
    rontal
    -0.72
    pora
    -0.71
    occup
    -0.70
    apa
    -0.68
    andro
    -0.68
    idency
    -0.66
    POSITIVE LOGITS
     wizard
    1.29
     Wizard
    1.09
    izard
    0.94
    sonian
    0.89
    ãĥ¼ãĥĨãĤ£
    0.85
     Voldemort
    0.85
     wizards
    0.82
    ry
    0.77
     Hogwarts
    0.76
    eering
    0.75
    Activations Density 0.010%

    No Known Activations