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. 11-RES-JB
    6. 17940
    Prev
    Next
    INDEX
    Explanations

    terms related to freedom of expression and civil rights

    oai_token-act-pair · gpt-3.5-turbo

    discussions related to freedom of expression and civil liberties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Surge
    -0.74
     Gund
    -0.67
     HELP
    -0.66
     Lauder
    -0.65
     Slim
    -0.62
    soDeliveryDate
    -0.62
     Handler
    -0.60
     Loren
    -0.59
     Vet
    -0.59
     Benz
    -0.59
    POSITIVE LOGITS
     expression
    1.18
     speech
    1.15
     dissent
    1.11
     Expression
    1.10
    expression
    1.09
     conscience
    1.02
     freedom
    0.98
    speech
    0.97
     liberty
    0.95
     expressive
    0.95
    Activations Density 0.274%

    No Known Activations