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. 19067
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "iber", possibly referring to "cyber" or "fiber"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "fiber" in various contexts

    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
     pity
    -0.67
    ĸļ
    -0.66
    pread
    -0.63
     untreated
    -0.63
    atche
    -0.62
    urations
    -0.61
     undone
    -0.60
    isters
    -0.59
    words
    -0.59
     Michaels
    -0.58
    POSITIVE LOGITS
    iber
    1.09
    tarian
    1.08
    glass
    1.05
    tarians
    0.99
    ulent
    0.83
    glas
    0.82
    gins
    0.79
    culus
    0.78
    oad
    0.78
    ling
    0.75
    Activations Density 0.008%

    No Known Activations