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. 0-RES-JB
    6. 4634
    Prev
    Next
    INDEX
    Explanations

    adverbs representing speed or immediacy

    oai_token-act-pair · gpt-3.5-turbo

    words associated with promptness and duty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autobi
    -0.76
    odes
    -0.67
     foundation
    -0.61
    ophon
    -0.61
     Anim
    -0.60
     Unch
    -0.59
    bind
    -0.59
     Strong
    -0.58
    diff
    -0.57
     layer
    -0.57
    POSITIVE LOGITS
     promptly
    3.47
     duly
    1.85
     swiftly
    1.36
     gladly
    1.35
     conspic
    1.22
     proceeded
    1.22
     politely
    1.10
     predictably
    1.08
     prominently
    1.06
     conveniently
    1.06
    Activations Density 0.025%

    No Known Activations