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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 3679
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of common sense

    oai_token-act-pair · gpt-3.5-turbo

    references to "common sense" in various contexts

    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
    atern
    -0.74
    leased
    -0.71
    boxing
    -0.70
    soon
    -0.70
    rose
    -0.65
    ench
    -0.64
    ISS
    -0.64
    Stars
    -0.62
    usky
    -0.60
    ouched
    -0.60
    POSITIVE LOGITS
    smanship
    0.96
     approach
    0.88
    abl
    0.83
     prud
    0.81
     prudent
    0.80
     prevailed
    0.80
     prag
    0.79
     Approach
    0.76
    ensical
    0.76
     decency
    0.74
    Activations Density 0.119%

    No Known Activations