Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 20857
    Prev
    Next
    INDEX
    Explanations

    information related to government policies, budgets, and economic impact

    oai_token-act-pair · gpt-3.5-turbo

    legislative terms and discussions related to government bills and sponsorships

    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
     Notting
    -0.99
     Aires
    -0.87
     realise
    -0.85
    asia
    -0.84
     realised
    -0.83
    oeuv
    -0.83
    ramids
    -0.81
    CIA
    -0.81
    CHQ
    -0.79
     fulfil
    -0.79
    POSITIVE LOGITS
     statewide
    1.96
     Legislature
    1.93
     Gov
    1.76
     gubernatorial
    1.72
     governor
    1.67
     Governor
    1.62
     legislature
    1.61
     state
    1.56
    Gov
    1.48
     legislators
    1.46
    Activations Density 0.753%

    No Known Activations