Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 17512
    Prev
    Next
    INDEX
    Explanations

    legal terms and phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to legal terms and court-related phrases

    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
     beaut
    -0.77
     lovers
    -0.75
     Meteor
    -0.72
     condol
    -0.70
     bun
    -0.69
     hooked
    -0.68
     Bom
    -0.67
    ctors
    -0.67
     smokes
    -0.67
     meteor
    -0.67
    POSITIVE LOGITS
    Footnote
    1.00
    âĢł
    0.99
    ¶
    0.96
    ¤
    0.93
    §
    0.93
    º
    0.91
     Petition
    0.86
    ĸļ
    0.84
    Court
    0.83
     JUSTICE
    0.83
    Activations Density 0.353%

    No Known Activations