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. 1070
    Prev
    Next
    INDEX
    Explanations

    legalese and technical legal terms

    oai_token-act-pair · gpt-3.5-turbo

    judicial reasoning and legal terminology

    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
     pige
    -0.59
     monog
    -0.57
     prostitutes
    -0.53
     sexually
    -0.51
     ecstasy
    -0.48
    Picture
    -0.48
     virginity
    -0.48
     rav
    -0.48
     Somerset
    -0.48
    Girls
    -0.47
    POSITIVE LOGITS
     nomine
    0.60
    govtrack
    0.55
    });
    0.54
     proprietary
    0.53
     conclud
    0.52
    />
    0.51
    anwhile
    0.50
    emption
    0.50
     consulted
    0.50
    >.
    0.49
    Activations Density 1.642%

    No Known Activations