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. 10-RES-JB
    6. 13362
    Prev
    Next
    INDEX
    Explanations

    references to political events or gatherings

    oai_token-act-pair · gpt-3.5-turbo

    the term "rally" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iencies
    -0.71
     Dictionary
    -0.70
    etheless
    -0.67
    abilities
    -0.64
    missions
    -0.63
    ahime
    -0.62
    ately
    -0.61
    pei
    -0.61
     Fiction
    -0.61
     Leopard
    -0.60
    POSITIVE LOGITS
     rally
    1.13
     rallies
    1.05
    isers
    0.94
    goers
    0.92
     Rally
    0.90
     denouncing
    0.90
     organizer
    0.89
     attendees
    0.89
     organisers
    0.89
     marches
    0.88
    Activations Density 0.034%

    No Known Activations