Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 5-RES-JB
    6. 15509
    Prev
    Next
    INDEX
    Explanations

    references to medical doctors

    oai_token-act-pair · gpt-3.5-turbo

    sentences that contain the term "Dr." followed by a name, indicating references to physicians or medical professionals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fml
    -0.71
    ahime
    -0.70
     coincide
    -0.69
     calendars
    -0.69
     commercially
    -0.67
     tenancy
    -0.65
     chilled
    -0.64
     cohesive
    -0.63
     controllers
    -0.63
    obyl
    -0.63
    POSITIVE LOGITS
    ItemTracker
    0.92
     Jill
    0.91
     Eug
    0.79
    icio
    0.78
     âĸĪ
    0.76
     Bruce
    0.75
     Jo
    0.72
     Joel
    0.72
    insert
    0.72
     Sho
    0.72
    Activations Density 0.028%

    No Known Activations