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. 3688
    Prev
    Next
    INDEX
    Explanations

    political affiliations, specifically related to the Conservative Party

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Conservative Party

    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
    ulla
    -0.81
    emis
    -0.69
    atl
    -0.66
     shields
    -0.66
    }}}
    -0.65
     scrim
    -0.65
     legends
    -0.64
    ysis
    -0.64
    maps
    -0.63
    lets
    -0.63
    POSITIVE LOGITS
     Conservative
    3.83
     Conservatives
    3.04
    Conservative
    2.79
     Tory
    2.52
     Liberal
    2.40
     Tories
    2.30
    Liberal
    2.05
     Liberals
    2.03
     NDP
    1.87
     Labour
    1.71
    Activations Density 0.016%

    No Known Activations