© 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. 10-RES-JB
    11. 10749
    Prev
    Next
    INDEX
    Explanations

    references to the geographical location "Oz", possibly related to the fictional Land of Oz

    oai_token-act-pair · gpt-3.5-turbo

    references to "Oz," likely relating to "The Wizard of Oz" or its associated themes and characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     à¤
    -0.67
    ivities
    -0.66
    ————————————————
    -0.62
     Scots
    -0.62
     Chr
    -0.62
     Columb
    -0.61
    ivity
    -0.59
     furnish
    -0.58
     WITHOUT
    -0.58
    ISTER
    -0.57
    POSITIVE LOGITS
    pin
    1.08
    aukee
    1.01
    ark
    0.87
    arks
    0.82
    tur
    0.80
    eki
    0.79
    mology
    0.78
    gur
    0.77
    mos
    0.77
    dem
    0.77
    Activations Density 0.070%

    No Known Activations