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. 6-RES-JB
    6. 82
    Prev
    Next
    INDEX
    Explanations

    keywords related to legal actions, specifically extradition

    oai_token-act-pair · gpt-3.5-turbo

    terms related to extradition and legal processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Parenthood
    -0.79
     Mercury
    -0.76
     wrench
    -0.74
     Baal
    -0.64
     Mars
    -0.62
     Pompe
    -0.60
     Haas
    -0.60
    onew
    -0.60
    hift
    -0.59
     pse
    -0.57
    POSITIVE LOGITS
    arnaev
    0.93
    ileaks
    0.90
    riter
    0.89
    reement
    0.85
    iting
    0.83
    otos
    0.81
     GOODMAN
    0.80
    raq
    0.79
    ited
    0.79
     Annotations
    0.76
    Activations Density 0.068%

    No Known Activations