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. 9-RES-JB
    6. 519
    Prev
    Next
    INDEX
    Explanations

    specific mentions of entities (e.g., organizations, locations, individuals)

    oai_token-act-pair · gpt-3.5-turbo

    phrases referencing law enforcement or legal actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    opsis
    -0.78
     preceded
    -0.77
    worn
    -0.76
     followed
    -0.69
    auntlet
    -0.67
    ingen
    -0.66
    arrow
    -0.65
    pread
    -0.65
     namely
    -0.64
    çĭ
    -0.64
    POSITIVE LOGITS
     Ministry
    1.23
     Department
    1.16
     feds
    1.12
     Office
    1.01
     Bureau
    1.01
     ACLU
    0.99
     manufacturer
    0.99
     Centers
    0.99
     Dept
    0.98
     FBI
    0.97
    Activations Density 0.399%

    No Known Activations