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. 3928
    Prev
    Next
    INDEX
    Explanations

    references to political parties

    oai_token-act-pair · gpt-3.5-turbo

    references to political parties

    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
     Archangel
    -0.78
    Downloadha
    -0.70
    ":["
    -0.69
     Raphael
    -0.66
    eval
    -0.66
    âĸĪâĸĪâĸĪâĸĪ
    -0.65
     McMaster
    -0.64
    OIL
    -0.63
    estine
    -0.63
    ulla
    -0.63
    POSITIVE LOGITS
     party
    3.77
    party
    2.88
     Party
    2.88
    Party
    2.86
     parties
    2.69
     Parties
    2.34
     PART
    1.29
     caucus
    1.27
     partisan
    1.07
     DNC
    1.06
    Activations Density 0.022%

    No Known Activations