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. 11-RES-JB
    6. 8721
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal and procedural matters

    oai_token-act-pair · gpt-3.5-turbo

    personal pronouns and expressions of sentiment or action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Newsletter
    -0.62
    ital
    -0.61
     enhances
    -0.61
     Enh
    -0.60
     measurable
    -0.59
    amiliar
    -0.59
    reetings
    -0.59
    democratic
    -0.57
    avorable
    -0.57
    levant
    -0.57
    POSITIVE LOGITS
     resorted
    1.40
     consequently
    1.03
     therefore
    1.02
     instead
    1.00
     blame
    0.98
     stranded
    0.97
     unable
    0.95
     unus
    0.94
     blamed
    0.92
     blames
    0.92
    Activations Density 0.536%

    No Known Activations