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. 10-RES-JB
    6. 7372
    Prev
    Next
    INDEX
    Explanations

    mentions or discussions of political endorsements

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "endorsement" and related terms

    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
    bang
    -0.75
    %);
    -0.70
    istor
    -0.70
    borg
    -0.68
    iland
    -0.67
     nerv
    -0.67
    cock
    -0.66
    STEM
    -0.65
    brance
    -0.64
    awar
    -0.64
    POSITIVE LOGITS
     endorsing
    1.13
     endorsements
    1.08
     endorsement
    1.06
     candidate
    1.00
     endorse
    0.96
     candidacy
    0.94
     endorsed
    0.91
     endors
    0.89
     candidates
    0.84
     disav
    0.82
    Activations Density 0.054%

    No Known Activations