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. 7-RES-JB
    6. 12953
    Prev
    Next
    INDEX
    Explanations

    phrases related to freedom, openness, and societal issues

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of freedom and its related terms

    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
     Miko
    -0.79
    ²¾
    -0.77
    »Ĵ
    -0.75
    ĪĴ
    -0.71
    soDeliveryDate
    -0.71
    ashtra
    -0.69
     Reviews
    -0.68
     Heads
    -0.68
    vae
    -0.67
    TPS
    -0.67
    POSITIVE LOGITS
     roam
    0.83
    Initialized
    0.80
    ktop
    0.72
     improv
    0.70
    ercise
    0.70
    ruary
    0.68
    owship
    0.66
     slaves
    0.66
     ebook
    0.63
    tein
    0.63
    Activations Density 0.149%

    No Known Activations