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. 11-RES-JB
    6. 3954
    Prev
    Next
    INDEX
    Explanations

    organizations and centers providing support and services to communities, with a focus on health and housing for vulnerable populations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to health and wellness services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    beard
    -0.78
    bda
    -0.72
    peror
    -0.71
    poll
    -0.71
    yrights
    -0.71
    opoly
    -0.70
    chev
    -0.70
    SpaceEngineers
    -0.69
    wikipedia
    -0.69
    estamp
    -0.69
    POSITIVE LOGITS
     clinics
    1.57
     counselling
    1.48
     clinic
    1.44
     counselors
    1.43
     counseling
    1.42
     outpatient
    1.41
     hotline
    1.26
     hosp
    1.26
     therapists
    1.26
     shelters
    1.22
    Activations Density 0.556%

    No Known Activations