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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 18605
    Prev
    Next
    INDEX
    Explanations

    references to various political figures and candidates

    oai_token-act-pair · gpt-3.5-turbo

    names and references related to political candidates in elections

    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
    ĸļ
    -0.81
    rawdownloadcloneembedreportprint
    -0.79
    Reviewer
    -0.76
    zsche
    -0.70
    canon
    -0.66
    endum
    -0.64
    sson
    -0.63
     Libraries
    -0.63
    netflix
    -0.62
    cients
    -0.62
    POSITIVE LOGITS
     Hillary
    0.99
     runoff
    0.93
     candidate
    0.93
    Hillary
    0.90
     nominee
    0.89
     challenger
    0.88
     incumbent
    0.86
     Democrat
    0.86
     Mitt
    0.85
     Romney
    0.84
    Activations Density 0.171%

    No Known Activations