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. 6-RES-JB
    6. 1896
    Prev
    Next
    INDEX
    Explanations

    phrases related to politics and policies, particularly focused on healthcare and government programs

    oai_token-act-pair · gpt-3.5-turbo

    references to political and legislative issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ui
    -0.73
    iri
    -0.68
    cil
    -0.63
    antz
    -0.62
    iazep
    -0.62
    iple
    -0.61
    edi
    -0.60
     pengu
    -0.59
    actic
    -0.58
     Yi
    -0.58
    POSITIVE LOGITS
    whatever
    0.64
     overseen
    0.64
     Digest
    0.63
    TPP
    0.59
    dq
    0.59
     ObamaCare
    0.58
     itself
    0.57
    despite
    0.57
    atron
    0.56
     guaranteeing
    0.56
    Activations Density 0.760%

    No Known Activations