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. 0-RES-JB
    6. 22835
    Prev
    Next
    INDEX
    Explanations

    medical terms related to health and medical conditions, specifically focusing on fertility and temperature

    oai_token-act-pair · gpt-3.5-turbo

    terms related to fertility and its factors

    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
    esan
    -0.70
    read
    -0.63
    AAF
    -0.63
    oway
    -0.60
    amia
    -0.59
    NESS
    -0.59
    cycl
    -0.59
    taboola
    -0.59
     certs
    -0.58
     pupil
    -0.57
    POSITIVE LOGITS
    Point
    0.71
     Destination
    0.69
    nox
    0.67
    Rush
    0.66
    rontal
    0.65
    eele
    0.63
    RT
    0.62
    ouble
    0.62
    ourced
    0.61
    atching
    0.61
    Activations Density 0.000%

    No Known Activations