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. 9-RES-JB
    6. 293
    Prev
    Next
    INDEX
    Explanations

    names of politicians and political parties

    oai_token-act-pair · gpt-3.5-turbo

    mentions of prominent political figures and their affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     withd
    -0.68
     newcom
    -0.61
     SAR
    -0.60
     conclud
    -0.60
     CentOS
    -0.58
     Agric
    -0.58
     scrut
    -0.58
    Oper
    -0.58
     auxiliary
    -0.56
     redes
    -0.56
    POSITIVE LOGITS
     "
    0.94
     disgrace
    0.93
     "'
    0.90
     unfairly
    0.88
     impe
    0.87
     rigged
    0.85
     "#
    0.85
     hypocritical
    0.85
     "â̦
    0.84
     deserved
    0.83
    Activations Density 0.830%

    No Known Activations