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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 11697
    Prev
    Next
    INDEX
    Explanations

    superlatives and comparative terms such as "easiest," "closest," "best," and "most."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to ease and quality of solutions or options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    azard
    -0.76
    avis
    -0.70
    ammed
    -0.68
    senal
    -0.66
    discrimination
    -0.64
    ustom
    -0.64
    ipel
    -0.63
    apesh
    -0.63
    ilater
    -0.62
    historic
    -0.62
    POSITIVE LOGITS
     thing
    0.89
     downside
    0.88
     question
    0.87
     reason
    0.82
     difference
    0.79
     explanation
    0.79
     drawback
    0.78
     exception
    0.77
     straw
    0.77
     caveat
    0.77
    Activations Density 0.173%

    No Known Activations