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. 24025
    Prev
    Next
    INDEX
    Explanations

    references to legal regulations in specific geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    references to the District of Columbia

    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
    zsche
    -0.88
    ttp
    -0.82
    tons
    -0.81
     clutch
    -0.80
    wcs
    -0.77
    natureconservancy
    -0.71
    Reviewer
    -0.71
    phrine
    -0.67
    etheus
    -0.67
    ItemTracker
    -0.67
    POSITIVE LOGITS
     Detail
    0.71
     Richmond
    0.70
     Guerrero
    0.70
     Browns
    0.69
     Detention
    0.68
     Regions
    0.67
     Commerce
    0.67
     Valencia
    0.66
     Reyn
    0.66
     Columbia
    0.66
    Activations Density 0.059%

    No Known Activations