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. 4706
    Prev
    Next
    INDEX
    Explanations

    the word "besides" followed by another word or phrase

    oai_token-act-pair · gpt-3.5-turbo

    the word "besides" and its variants

    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
    ardy
    -0.61
    ulin
    -0.57
    aroo
    -0.55
     Daily
    -0.53
     findings
    -0.53
     result
    -0.52
     pattern
    -0.52
    iling
    -0.52
     response
    -0.52
     Northern
    -0.51
    POSITIVE LOGITS
     besides
    3.72
     Besides
    1.82
    Besides
    1.71
    esides
    1.71
     moreover
    1.45
     furthermore
    1.42
     namely
    1.38
     apart
    1.31
     except
    1.26
     secondly
    1.26
    Activations Density 0.004%

    No Known Activations