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. 8-RES-JB
    6. 20563
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "clinic"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of medical clinics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lass
    -0.76
    lasses
    -0.71
    trap
    -0.69
    lust
    -0.67
    gest
    -0.66
    recy
    -0.64
     sqor
    -0.63
    sum
    -0.63
     quot
    -0.62
     lyr
    -0.62
    POSITIVE LOGITS
     clinic
    0.88
     Clinic
    0.86
    opath
    0.85
     clinics
    0.79
     specializing
    0.79
     Patients
    0.75
     patient
    0.74
     attendant
    0.74
     pharmacy
    0.73
    idges
    0.71
    Activations Density 0.044%

    No Known Activations