Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 0-RES-JB
    6. 21603
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Liberty"

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "Liberty."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĶ
    -0.86
    én
    -0.81
    dj
    -0.76
    âĢ
    -0.71
    ð
    -0.70
    sth
    -0.69
     epis
    -0.69
     underestimate
    -0.68
     reapp
    -0.67
    ÅĤ
    -0.67
    POSITIVE LOGITS
     Liberty
    4.11
    Liber
    2.08
     liberty
    1.93
     Freedom
    1.75
    Freedom
    1.51
     Liber
    1.44
    liber
    1.44
     Libertarian
    1.43
     Liberties
    1.43
     Independence
    1.34
    Activations Density 0.011%

    No Known Activations