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. 7-RES-JB
    6. 3480
    Prev
    Next
    INDEX
    Explanations

    political figures and leaders

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names of political figures and associated titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    boards
    -0.72
     Kru
    -0.66
     Shiv
    -0.63
    ãĤ©
    -0.63
    minist
    -0.60
     printers
    -0.55
    docs
    -0.55
    ights
    -0.55
    arist
    -0.54
    DNA
    -0.54
    POSITIVE LOGITS
     Jr
    0.82
     respectively
    0.81
    Jr
    0.79
    bane
    0.76
     whom
    0.71
     helicop
    0.68
     III
    0.67
    rompt
    0.67
     TAMADRA
    0.66
    enstein
    0.65
    Activations Density 0.246%

    No Known Activations