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. 6-RES-JB
    6. 6663
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical conditions or natural disasters

    oai_token-act-pair · gpt-3.5-turbo

    terms related to diagnosis and medical conditions

    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
    ting
    -0.91
    ted
    -0.82
    ters
    -0.80
    TING
    -0.78
    BOOK
    -0.76
    DOM
    -0.73
    FORE
    -0.72
    BOX
    -0.72
    ween
    -0.71
    ter
    -0.71
    POSITIVE LOGITS
    ostic
    1.41
    ostics
    1.17
    ificent
    1.09
    ificant
    1.04
    itude
    0.97
    animous
    0.93
    osis
    0.87
    ados
    0.87
    olini
    0.86
    ancy
    0.83
    Activations Density 0.015%

    No Known Activations