© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 15182
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal actions or filings

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legal filings and lawsuits

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

    No Comments

    Negative Logits
    ãĤ©
    -0.75
    cakes
    -0.75
    warts
    -0.70
     Egyptians
    -0.68
    pher
    -0.67
    iev
    -0.67
    terness
    -0.66
    ahime
    -0.66
     Ramadan
    -0.62
    ory
    -0.61
    POSITIVE LOGITS
     arbitration
    0.87
    idav
    0.77
    isance
    0.76
     folders
    0.76
    ãģĨ
    0.75
    roleum
    0.72
    ancies
    0.72
     directories
    0.71
     registry
    0.71
     affidavit
    0.70
    Activations Density 0.163%

    No Known Activations