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. 8-RES-JB
    6. 18059
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases indicating a location or context

    oai_token-act-pair · gpt-3.5-turbo

    the word "in" and its various uses within sentences

    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
    lic
    -0.67
    hett
    -0.63
    llor
    -0.62
    ptive
    -0.60
    interrupted
    -0.60
    estamp
    -0.60
    lik
    -0.59
    po
    -0.57
    artment
    -0.55
    Life
    -0.55
    POSITIVE LOGITS
     disguise
    1.26
     sorts
    0.81
    retty
    0.71
    Þ
    0.68
    \\\\
    0.67
     nomine
    0.67
    WithNo
    0.67
    version
    0.66
     steroids
    0.64
     nature
    0.64
    Activations Density 0.282%

    No Known Activations