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

    Neuronpedia

    APICircuit 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. 6681
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions being carried out or conducted

    oai_token-act-pair · gpt-3.5-turbo

    actions related to execution and completion of tasks or processes

    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
    assi
    -0.77
     Flavoring
    -0.74
    rium
    -0.65
     passage
    -0.62
    orum
    -0.61
     Selected
    -0.59
    Scroll
    -0.57
    akia
    -0.56
     Origin
    -0.55
     formation
    -0.55
    POSITIVE LOGITS
     differently
    1.21
     indoors
    0.99
     elsewhere
    0.98
     solely
    0.95
     electronically
    0.94
     concurrently
    0.94
     correctly
    0.93
     cheaply
    0.91
     inconsist
    0.90
     incorrectly
    0.90
    Activations Density 0.305%

    No Known Activations