© 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. 10-RES-JB
    11. 24024
    Prev
    Next
    INDEX
    Explanations

    words related to legal actions, such as pardons, exonerations, abstentions in votes, and extraditions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal actions and outcomes, particularly involving abstentions, pardons, and exonerations

    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
    é¾įå¥ij士
    -0.80
     behavi
    -0.70
     econom
    -0.69
     precon
    -0.67
     superf
    -0.66
     similarities
    -0.64
     flaws
    -0.64
     imperfect
    -0.63
     idi
    -0.62
     inequalities
    -0.62
    POSITIVE LOGITS
    ained
    1.14
    ched
    1.11
    ching
    1.01
    uating
    1.01
    iled
    1.00
    elling
    1.00
    uted
    0.99
    aped
    0.99
    ared
    0.99
    icated
    0.98
    Activations Density 0.107%

    No Known Activations