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. 0-RES-JB
    6. 17523
    Prev
    Next
    INDEX
    Explanations

    adjectives referring to large or significant amounts

    oai_token-act-pair · gpt-3.5-turbo

    references to significant quantities or amounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tap
    -0.66
     reminds
    -0.66
    remember
    -0.65
    speak
    -0.63
    Ask
    -0.63
     vs
    -0.61
     remembers
    -0.61
    always
    -0.61
    fen
    -0.61
    ophobia
    -0.60
    POSITIVE LOGITS
     substantial
    3.05
     sizeable
    2.29
     sizable
    2.22
     considerable
    2.14
     significant
    2.09
     substantive
    1.78
    stantial
    1.76
    significant
    1.74
     substantially
    1.61
     hefty
    1.59
    Activations Density 0.014%

    No Known Activations