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. 7-RES-JB
    6. 10723
    Prev
    Next
    INDEX
    Explanations

    the word "nut" or related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to nuts, particularly the word "nut" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    interstitial
    -0.76
     Esper
    -0.64
     Stevenson
    -0.63
    naire
    -0.63
     Yamato
    -0.62
     Plat
    -0.61
     Sparrow
    -0.61
     tou
    -0.61
     Vaj
    -0.61
     payable
    -0.61
    POSITIVE LOGITS
    ritional
    1.46
    rient
    1.37
    rients
    1.35
    rition
    1.23
    meg
    1.22
    tle
    1.07
    tall
    1.04
    ricia
    0.94
    ella
    0.92
    bush
    0.92
    Activations Density 0.029%

    No Known Activations