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. 10-RES-JB
    6. 14457
    Prev
    Next
    INDEX
    Explanations

    ways to solve problems or make discoveries

    oai_token-act-pair · gpt-3.5-turbo

    phrases centered around the concept of searching for solutions or information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    panic
    -0.79
    idium
    -0.77
    cour
    -0.70
    ember
    -0.70
    eka
    -0.66
    ossession
    -0.63
    rush
    -0.63
    mort
    -0.63
    ICO
    -0.62
    heit
    -0.62
    POSITIVE LOGITS
     ways
    1.41
     solutions
    1.21
     loopholes
    1.20
     somew
    1.18
     alternatives
    1.05
     replacements
    1.03
     answers
    1.00
     effic
    0.98
     excuses
    0.92
     suitable
    0.91
    Activations Density 0.075%

    No Known Activations