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. 11833
    Prev
    Next
    INDEX
    Explanations

    words related to government funding, support, and sponsorship

    oai_token-act-pair · gpt-3.5-turbo

    terms related to government involvement and support in various contexts

    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
    osponsors
    -0.98
    someone
    -0.88
    asso
    -0.84
    achu
    -0.80
    thia
    -0.73
    irlf
    -0.71
    ilk
    -0.71
    OTAL
    -0.71
    proven
    -0.70
    erning
    -0.70
    POSITIVE LOGITS
     enterprises
    0.91
     endeavour
    0.78
     enterprise
    0.75
     entity
    0.73
     entities
    0.71
     endeavor
    0.67
     Enterprises
    0.66
     successor
    0.66
     healthcare
    0.65
     monopoly
    0.65
    Activations Density 0.090%

    No Known Activations