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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 3860
    Prev
    Next
    INDEX
    Explanations

    words related to political entities like '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
    uko
    -0.70
     Accessed
    -0.68
     Fib
    -0.65
    ifer
    -0.63
    esson
    -0.61
    shield
    -0.61
     Archangel
    -0.60
    met
    -0.60
    eval
    -0.59
    agus
    -0.59
    POSITIVE LOGITS
     parties
    4.07
     Parties
    3.29
     party
    2.34
    party
    2.13
    Party
    2.06
     Party
    1.74
     clubs
    1.41
     sexes
    1.29
     factions
    1.19
     spouses
    1.18
    Activations Density 0.019%

    No Known Activations