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. 8-RES-JB
    6. 12122
    Prev
    Next
    INDEX
    Explanations

    phrases related to contracts, agreements, and legal actions

    oai_token-act-pair · gpt-3.5-turbo

    clauses that discuss contracts and obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ihil
    -0.78
    abilia
    -0.75
    lde
    -0.73
     mascul
    -0.70
    die
    -0.70
    isexual
    -0.69
    ãĤ¨ãĥ«
    -0.69
     syndrome
    -0.66
    aging
    -0.65
    osexual
    -0.65
    POSITIVE LOGITS
     moreover
    0.74
     Priority
    0.72
     unilaterally
    0.70
     Presumably
    0.70
     secondly
    0.70
     Therefore
    0.69
     ensuring
    0.69
     ISPs
    0.67
     ratified
    0.66
     Its
    0.66
    Activations Density 0.703%

    No Known Activations