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. 17751
    Prev
    Next
    INDEX
    Explanations

    mentions of various types of freedoms

    oai_token-act-pair · gpt-3.5-turbo

    references to freedoms and liberties

    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
    itch
    -0.68
    asu
    -0.66
     match
    -0.65
    iard
    -0.64
     Crist
    -0.64
    iti
    -0.63
    LV
    -0.63
    ep
    -0.62
    emi
    -0.61
    cephal
    -0.61
    POSITIVE LOGITS
     freedoms
    3.85
     freedom
    2.10
    freedom
    1.90
     liberties
    1.68
    Freedom
    1.56
     liberty
    1.49
     Freed
    1.49
     Freedom
    1.40
     privileges
    1.37
     licences
    1.31
    Activations Density 0.022%

    No Known Activations