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. 0-RES-JB
    6. 24423
    Prev
    Next
    INDEX
    Explanations

    combinations or pairing of elements

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "combinations."

    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
     Issue
    -0.83
    Dispatch
    -0.73
     Report
    -0.71
    issue
    -0.71
     stern
    -0.69
     Refugee
    -0.68
    ISC
    -0.68
    report
    -0.67
    cknowled
    -0.67
    fund
    -0.65
    POSITIVE LOGITS
     combinations
    3.44
     combos
    2.35
     combo
    1.68
     combining
    1.67
     hybrids
    1.53
     Comb
    1.52
     substit
    1.49
     combination
    1.37
     configurations
    1.37
     ratios
    1.35
    Activations Density 0.042%

    No Known Activations