Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 17384
    Prev
    Next
    INDEX
    Explanations

    references to singer and actress Miley Cyrus

    oai_token-act-pair · gpt-3.5-turbo

    the word "Mokey" and its variations, indicating references to a specific character or concept

    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
     surplus
    -0.68
     commod
    -0.62
     marginal
    -0.61
     Lub
    -0.61
    iterranean
    -0.60
     Honor
    -0.60
    ittance
    -0.60
     incidentally
    -0.59
     sorts
    -0.58
     à¨
    -0.58
    POSITIVE LOGITS
    oke
    1.38
    oking
    1.24
    otle
    0.89
    eper
    0.86
    oked
    0.86
    ffe
    0.86
    lear
    0.86
    gi
    0.83
    okes
    0.82
    vel
    0.82
    Activations Density 0.004%

    No Known Activations