© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 11987
    Prev
    Next
    INDEX
    Explanations

    references to the place or title "Oz."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Oz" and related references to the Wizard of Oz

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģį
    -0.67
    ãģ¦
    -0.66
     fries
    -0.62
    trl
    -0.61
    RAW
    -0.60
    士
    -0.59
    ++++++++++++++++
    -0.59
     delinqu
    -0.59
     inadequ
    -0.58
    Í
    -0.58
    POSITIVE LOGITS
    osta
    0.93
    rh
    0.87
    leys
    0.84
    boro
    0.83
     Oz
    0.82
    asar
    0.80
    elia
    0.79
    ey
    0.78
    eki
    0.77
    biz
    0.76
    Activations Density 0.032%

    No Known Activations