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. 2-RES-JB
    6. 1117
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical conditions, particularly those related to the thyroid gland

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the thyroid gland and associated medical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¶ħ
    -0.78
    ruciating
    -0.78
    lished
    -0.77
    asar
    -0.77
    andise
    -0.77
     councill
    -0.73
    asus
    -0.72
    icago
    -0.72
    acas
    -0.71
    ilyn
    -0.69
    POSITIVE LOGITS
    enance
    0.86
     Mobility
    0.77
    sie
    0.75
    levels
    0.75
    omething
    0.74
     Vegeta
    0.72
     Sequence
    0.69
    omatic
    0.69
     Turbo
    0.69
    ]=
    0.68
    Activations Density 0.019%

    No Known Activations