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. 11-RES-JB
    6. 11062
    Prev
    Next
    INDEX
    Explanations

    adjectives with the prefix 'non-' or the stem 'nucle'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 'n' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •·ΘΘΘΘ

    No Comments

    Negative Logits
     upside
    -0.73
     asleep
    -0.68
     frank
    -0.65
     slack
    -0.65
     contacting
    -0.63
     Vaj
    -0.63
     inund
    -0.59
     Agent
    -0.59
     cand
    -0.59
     lung
    -0.59
    POSITIVE LOGITS
    aturally
    1.45
    onsense
    1.45
    autical
    1.35
    umbers
    1.35
    aughty
    1.34
    umerous
    1.31
    ihil
    1.31
    aked
    1.30
    umbing
    1.28
    orthern
    1.28
    Activations Density 0.043%

    No Known Activations