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. 8-RES-JB
    6. 20915
    Prev
    Next
    INDEX
    Explanations

    verbs related to physical activities or skills

    oai_token-act-pair · gpt-3.5-turbo

    verbs and actions related to learning and skills acquisition

    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
    76561
    -0.70
    osure
    -0.63
    reements
    -0.62
    ptoms
    -0.61
    iations
    -0.61
    issues
    -0.61
     assurances
    -0.58
    Initial
    -0.58
    ordering
    -0.56
    Attempts
    -0.56
    POSITIVE LOGITS
     anymore
    1.08
     freely
    1.01
     responsibly
    0.94
     outdoors
    0.87
     efficiently
    0.86
     comfortably
    0.86
     anywhere
    0.83
     abroad
    0.82
     indoors
    0.82
     someday
    0.77
    Activations Density 0.345%

    No Known Activations