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. 4-RES-JB
    6. 21433
    Prev
    Next
    INDEX
    Explanations

    the word "somewhere" followed by an indicating number

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "somewhere" or expressions indicating location or placement

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

    No Comments

    Negative Logits
    iff
    -0.76
    iants
    -0.72
    root
    -0.67
    ios
    -0.66
     Griffith
    -0.64
    iere
    -0.63
    shock
    -0.62
    raid
    -0.61
    clus
    -0.61
    squ
    -0.60
    POSITIVE LOGITS
     else
    1.34
    Else
    1.28
     Else
    0.99
    ãĤ´ãĥ³
    0.91
    abouts
    0.88
    ĪĴ
    0.85
    £ı
    0.80
     Somewhere
    0.80
     somew
    0.78
     toget
    0.77
    Activations Density 0.009%

    No Known Activations