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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6-RES-JB
    11. 7962
    Prev
    Next
    INDEX
    Explanations

    legislation-related words and actions

    oai_token-act-pair · gpt-3.5-turbo

    references to legislative approval and voting processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Galile
    -0.76
    Pic
    -0.66
     recru
    -0.65
     nerv
    -0.63
     realised
    -0.63
    PLIED
    -0.62
     follower
    -0.61
     misunderstood
    -0.60
     frequ
    -0.60
     healer
    -0.60
    POSITIVE LOGITS
     unanimously
    1.13
     ratification
    0.93
    Draft
    0.89
     clot
    0.85
     amendments
    0.84
     authorizing
    0.81
     motions
    0.80
     petitions
    0.79
     confirmation
    0.78
     approving
    0.77
    Activations Density 0.225%

    No Known Activations