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. 2-RES-JB
    6. 18152
    Prev
    Next
    INDEX
    Explanations

    the name "Saw" occurring in various contexts or variations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific people, mainly those with the last name "Saw."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    izabeth
    -0.84
    urses
    -0.83
    ogue
    -0.82
    istically
    -0.81
    ysis
    -0.81
    issance
    -0.78
    icably
    -0.74
    omez
    -0.73
    ctica
    -0.71
    awei
    -0.71
    POSITIVE LOGITS
     Saw
    0.91
     Stronghold
    0.86
     Earn
    0.79
     Wage
    0.77
     Poster
    0.77
     Bearing
    0.76
     Parenthood
    0.76
     Cosponsors
    0.76
     Hots
    0.75
     Interest
    0.72
    Activations Density 0.024%

    No Known Activations