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. 10-RES-JB
    6. 9656
    Prev
    Next
    INDEX
    Explanations

    mentions of governmental positions specifically related to state governors

    oai_token-act-pair · gpt-3.5-turbo

    references to government officials or governors

    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
    theless
    -0.80
     sensit
    -0.70
     cockpit
    -0.65
     mast
    -0.63
    schild
    -0.62
     controllers
    -0.61
     cloud
    -0.60
     Primordial
    -0.60
     travellers
    -0.59
     civilisation
    -0.59
    POSITIVE LOGITS
    .,
    0.96
    inda
    0.90
    .-
    0.82
    elect
    0.81
    orter
    0.80
    .;
    0.79
    Gary
    0.78
    oration
    0.77
    essing
    0.76
    esse
    0.76
    Activations Density 0.012%

    No Known Activations