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. 8-RES-JB
    6. 21590
    Prev
    Next
    INDEX
    Explanations

    legal terms related to court actions and permissions

    oai_token-act-pair · gpt-3.5-turbo

    references to temporary legal or work arrangements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    riad
    -0.82
    ique
    -0.79
    ioch
    -0.78
    etus
    -0.78
    iosyncr
    -0.77
    heit
    -0.76
    htaking
    -0.75
    rics
    -0.74
    fman
    -0.74
    icion
    -0.73
    POSITIVE LOGITS
     restraining
    1.20
     truce
    0.98
     injunction
    0.93
     accommodation
    0.92
     lodging
    0.88
     halt
    0.86
    porary
    0.85
     temporary
    0.84
     moratorium
    0.83
     refuge
    0.83
    Activations Density 0.036%

    No Known Activations