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. 7-RES-JB
    6. 8328
    Prev
    Next
    INDEX
    Explanations

    mentions of legal cases and their details

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of a specific legal case

    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
    atomic
    -0.80
    erd
    -0.79
    ower
    -0.76
    lasses
    -0.75
    attery
    -0.73
    odes
    -0.72
    emouth
    -0.72
    uration
    -0.69
    pez
    -0.69
    icc
    -0.69
    POSITIVE LOGITS
     involving
    0.98
    cases
    0.93
     against
    0.84
     prosecuted
    0.84
     filed
    0.82
     histories
    0.77
     AGA
    0.72
    making
    0.72
    case
    0.70
    Attach
    0.69
    Activations Density 0.043%

    No Known Activations