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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 5008
    Prev
    Next
    INDEX
    Explanations

    legal jurisdiction-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to legal jurisdictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itches
    -0.73
    erm
    -0.73
    iked
    -0.70
    esta
    -0.70
    iq
    -0.69
    raid
    -0.68
    orns
    -0.68
    ighter
    -0.66
    ild
    -0.66
    hematic
    -0.66
    POSITIVE LOGITS
     jurisdiction
    1.05
    alties
    0.83
    abl
    0.81
    ignty
    0.77
     delegated
    0.73
     lobe
    0.70
     authority
    0.70
    atown
    0.70
    ability
    0.69
     boundaries
    0.68
    Activations Density 0.020%

    No Known Activations