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. 3-RES-JB
    6. 2682
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "ink" with varying activations, potentially focusing on different contexts or aspects of ink-related content

    oai_token-act-pair · gpt-3.5-turbo

    references to ink-related products, concepts, and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CVE
    -0.66
    ADS
    -0.66
    PsyNetMessage
    -0.65
    rals
    -0.64
     Roads
    -0.63
    âķIJâķIJ
    -0.61
    Interstitial
    -0.61
    nels
    -0.60
    OHN
    -0.60
     Aven
    -0.60
    POSITIVE LOGITS
     ink
    1.12
    jet
    1.02
    manship
    0.93
     cartridges
    0.86
    lings
    0.84
    prints
    0.82
     Ink
    0.82
    pots
    0.80
    weed
    0.80
    atha
    0.80
    Activations Density 0.015%

    No Known Activations