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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7856
    Prev
    Next
    INDEX
    Explanations

    names or surnames ending in 's'

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific character or symbol frequently mentioned in various contexts

    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
     scattering
    -0.74
     nurturing
    -0.73
     yield
    -0.72
     shelf
    -0.71
     envelope
    -0.71
     clinch
    -0.70
     filler
    -0.69
     disadvant
    -0.68
     trapping
    -0.68
     abound
    -0.67
    POSITIVE LOGITS
    said
    1.41
    ï¸ı
    1.37
    wrote
    1.13
    sent
    1.12
    told
    1.12
    has
    1.10
    didn
    1.02
    should
    1.01
    answered
    1.01
    signed
    1.00
    Activations Density 0.139%

    No Known Activations