© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 22542
    Prev
    Next
    INDEX
    Explanations

    legal and political terms and phrases

    oai_token-act-pair · gpt-3.5-turbo

    legislation and government-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mates
    -0.79
     onlook
    -0.78
     passers
    -0.77
     legends
    -0.74
     spectators
    -0.71
    phis
    -0.71
    itars
    -0.69
     visitors
    -0.69
     worldly
    -0.69
     viewers
    -0.68
    POSITIVE LOGITS
     Amendment
    1.13
     amendment
    1.07
     Amendments
    1.06
     Clause
    1.05
     clause
    1.04
    amacare
    1.00
    TPP
    0.98
     legislation
    0.96
     Directive
    0.94
     mandate
    0.93
    Activations Density 0.509%

    No Known Activations