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. 2-RES-JB
    6. 5022
    Prev
    Next
    INDEX
    Explanations

    names and titles of political leaders

    oai_token-act-pair · gpt-3.5-turbo

    titles and mentions of political leadership positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zl
    -0.74
    entric
    -0.73
     exting
    -0.70
    MpServer
    -0.68
    ether
    -0.68
    rawdownloadcloneembedreportprint
    -0.68
    schild
    -0.67
     mountainous
    -0.66
    agon
    -0.66
    condition
    -0.65
    POSITIVE LOGITS
     Leader
    1.13
    boards
    0.97
    Leader
    0.81
    doms
    0.79
     Candidate
    0.78
    leader
    0.76
     Tut
    0.76
    board
    0.73
    holder
    0.72
    esses
    0.71
    Activations Density 0.012%

    No Known Activations