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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7330
    Prev
    Next
    INDEX
    Explanations

    words related to widowhood or being widowed

    oai_token-act-pair · gpt-3.5-turbo

    terms related to widows and orphans

    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
     Cue
    -0.82
    Magikarp
    -0.75
    ��
    -0.71
    andise
    -0.70
    animal
    -0.69
    Item
    -0.68
    CG
    -0.67
    Cu
    -0.67
     ACC
    -0.67
    ERE
    -0.67
    POSITIVE LOGITS
     wid
    3.90
     widow
    2.74
     orphans
    2.25
     Widow
    1.99
    wid
    1.98
     Wid
    1.95
     orphan
    1.77
     cripp
    1.07
     unmarried
    1.07
     wives
    1.07
    Activations Density 0.048%

    No Known Activations