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. 10-RES-JB
    6. 17024
    Prev
    Next
    INDEX
    Explanations

    family relationships or locations within a family setting

    oai_token-act-pair · gpt-3.5-turbo

    references to familial relationships and specific individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocally
    -0.69
    使
    -0.58
     merit
    -0.55
    ãĥ¼ãĤ¯
    -0.55
     proven
    -0.54
     pertinent
    -0.54
     threat
    -0.52
    wcsstore
    -0.52
    notation
    -0.52
     generalized
    -0.52
    POSITIVE LOGITS
    's
    1.40
    ÃŃs
    1.12
    \'
    0.91
    ´
    0.88
    stown
    0.87
    house
    0.77
     bedrooms
    0.77
     offices
    0.76
     residence
    0.75
     bedroom
    0.75
    Activations Density 0.438%

    No Known Activations