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. 1-RES-JB
    6. 19221
    Prev
    Next
    INDEX
    Explanations

    text snippets related to legal documents, specifically affidavits

    oai_token-act-pair · gpt-3.5-turbo

    mentions of legal documents, specifically affidavits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oppers
    -0.73
    OPA
    -0.72
    obyl
    -0.71
    eric
    -0.68
    tics
    -0.67
    nic
    -0.67
    gone
    -0.65
     Nice
    -0.65
    enthal
    -0.65
    vernment
    -0.64
    POSITIVE LOGITS
     affidavit
    1.07
    idav
    0.94
     affidav
    0.83
     synopsis
    0.82
     warr
    0.76
     conclud
    0.76
     informant
    0.71
     agre
    0.71
     testimonies
    0.69
    inet
    0.69
    Activations Density 0.008%

    No Known Activations