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

    Neuronpedia

    APICircuit 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. 0-RES-JB
    6. 23893
    Prev
    Next
    INDEX
    Explanations

    political terms related to leadership positions and government actions

    oai_token-act-pair · gpt-3.5-turbo

    references to minority and majority leaders in a political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hex
    -0.80
     curl
    -0.75
    SI
    -0.75
     shell
    -0.70
     ox
    -0.68
    elin
    -0.67
    rax
    -0.66
    Es
    -0.66
     ho
    -0.66
     paddle
    -0.65
    POSITIVE LOGITS
     Minority
    3.81
     Majority
    2.20
    ority
    1.36
     Speaker
    1.17
     minority
    1.16
     Oversight
    1.11
     Resident
    1.11
    Senate
    1.06
    Democrats
    1.03
    Democratic
    0.99
    Activations Density 0.023%

    No Known Activations