© 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. 0-RES-JB
    11. 6165
    Prev
    Next
    INDEX
    Explanations

    the word "aunt" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "aunt."

    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
     circulation
    -0.77
     Fine
    -0.74
     yeast
    -0.71
     stabil
    -0.65
     iodine
    -0.65
     mercury
    -0.64
     jur
    -0.63
     iod
    -0.63
     consensus
    -0.63
     Code
    -0.62
    POSITIVE LOGITS
    aunts
    4.02
    aunt
    3.92
    aunted
    3.16
    aunting
    3.12
     taunt
    1.21
    irted
    1.02
    aun
    1.02
    ogging
    1.01
    alker
    1.00
    akedown
    0.97
    Activations Density 0.013%

    No Known Activations