© 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. 11-RES-JB
    11. 14890
    Prev
    Next
    INDEX
    Explanations

    phrases related to legislative and political processes

    oai_token-act-pair · gpt-3.5-turbo

    actions related to legislative processes and governmental functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quartered
    -0.70
     horr
    -0.70
    blogspot
    -0.67
    amous
    -0.67
    ÏĤ
    -0.67
    CVE
    -0.67
    agar
    -0.64
     Whilst
    -0.64
    ombat
    -0.64
    bourne
    -0.63
    POSITIVE LOGITS
     amendments
    1.14
     any
    1.00
     revisions
    1.00
     motions
    0.99
     recommendations
    0.99
     anything
    0.98
     additional
    0.98
     ratification
    0.97
     another
    0.96
     meaningful
    0.95
    Activations Density 0.295%

    No Known Activations