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. 5393
    Prev
    Next
    INDEX
    Explanations

    phrases containing the character string "asc" with a high emphasis on the specific sequence "asc" occurring as a standalone word

    oai_token-act-pair · gpt-3.5-turbo

    the word "asc" and its variations, indicating a focus on ascending or rising themes

    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
    STER
    -0.80
     stale
    -0.70
    giving
    -0.66
     Keynes
    -0.64
    gets
    -0.63
    frame
    -0.63
    tons
    -0.61
     Kers
    -0.61
    assetsadobe
    -0.61
    chard
    -0.61
    POSITIVE LOGITS
    ribed
    1.22
    adia
    1.21
    adian
    1.12
    ription
    1.05
    endant
    1.03
    ribe
    1.02
    henko
    1.01
    urred
    1.00
    itals
    0.98
    ript
    0.97
    Activations Density 0.007%

    No Known Activations