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. 6-RES-JB
    6. 4504
    Prev
    Next
    INDEX
    Explanations

    names of individuals involved in various incidents or events

    oai_token-act-pair · gpt-3.5-turbo

    names and identifying details of individuals involved in criminal cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     optim
    -0.86
     mathemat
    -0.84
     bookmark
    -0.82
     pse
    -0.79
    lished
    -0.78
     relativity
    -0.76
    olkien
    -0.74
     prediction
    -0.73
     forecasting
    -0.73
     philos
    -0.71
    POSITIVE LOGITS
     Doe
    1.09
     Tsarnaev
    1.00
    quez
    0.95
     Martinez
    0.89
    arnaev
    0.88
    endez
    0.86
    esville
    0.85
     Bundy
    0.84
     defendant
    0.84
     Fairfax
    0.83
    Activations Density 0.502%

    No Known Activations