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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 9027
    Prev
    Next
    INDEX
    Explanations

    political parties and organizations, particularly ones related to Kurdistan Workers' Party (PKK) and Democratic Party

    oai_token-act-pair · gpt-3.5-turbo

    political party names and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     climates
    -0.71
    wine
    -0.68
     wrinkles
    -0.66
     atmosp
    -0.65
     trumpet
    -0.65
     bets
    -0.65
    angelo
    -0.64
     billing
    -0.63
     saf
    -0.63
     adm
    -0.63
    POSITIVE LOGITS
     Party
    1.37
     Struggle
    1.26
     Movement
    1.22
     Front
    1.18
     Committees
    1.09
     Liberation
    1.07
     Organisation
    1.04
     Parties
    0.98
     Revolutionary
    0.98
     Revolution
    0.98
    Activations Density 0.116%

    No Known Activations