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. 16204
    Prev
    Next
    INDEX
    Explanations

    specific references to ballot propositions

    oai_token-act-pair · gpt-3.5-turbo

    references to specific propositions and legislation

    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
    soever
    -0.75
    keeper
    -0.74
    Interstitial
    -0.74
     fingertips
    -0.68
    esome
    -0.68
    WAYS
    -0.67
     Confederacy
    -0.65
     Carnegie
    -0.63
    arya
    -0.63
    cules
    -0.62
    POSITIVE LOGITS
    aganda
    1.23
    onents
    1.22
    onent
    1.17
    ensity
    1.16
    osed
    1.16
    osition
    1.07
    ulsion
    1.07
    itious
    1.04
    ylene
    0.99
    ulsive
    0.99
    Activations Density 0.030%

    No Known Activations