© 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. 0-RES-JB
    11. 9439
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific character or concept, such as "Aunt Jemima"

    oai_token-act-pair · gpt-3.5-turbo

    references to the character Aunt Jemima and related themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     antioxid
    -0.92
    Balt
    -0.79
     behavi
    -0.69
    DAQ
    -0.66
    PDATE
    -0.64
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.64
    HUD
    -0.63
    RESULTS
    -0.62
     adolesc
    -0.62
    GROUP
    -0.62
    POSITIVE LOGITS
    ividual
    0.86
    itially
    0.81
    ogun
    0.76
     ItemLevel
    0.75
    ecause
    0.73
    enfranch
    0.72
    othal
    0.69
    uilt
    0.65
     BaseType
    0.64
    ocaly
    0.62
    Activations Density 2.558%

    No Known Activations