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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 18398
    Prev
    Next
    INDEX
    Explanations

    alphanumeric patterns or sequences that include specific characters and numbers

    oai_token-act-pair · gpt-3.5-turbo

    special characters or variables in a mathematical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    raints
    -0.88
    enegger
    -0.80
    ometimes
    -0.73
    ounced
    -0.72
    ifiers
    -0.69
     consolidation
    -0.69
     IPM
    -0.68
    iazep
    -0.68
    sylvania
    -0.67
    ifier
    -0.67
    POSITIVE LOGITS
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    1.01
    âĶĢâĶĢâĶĢâĶĢ
    0.97
    λ
    0.90
    Ģ
    0.90
    ï¸ı
    0.86
    ptic
    0.82
    ELY
    0.81
    ques
    0.80
    llan
    0.79
    qua
    0.78
    Activations Density 0.012%

    No Known Activations