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. 21382
    Prev
    Next
    INDEX
    Explanations

    words related to payment or pricing

    oai_token-act-pair · gpt-3.5-turbo

    the term "per" in various contexts related to frequency or rate

    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
     Carbuncle
    -0.76
     Avalon
    -0.62
     pneum
    -0.61
     Scarlet
    -0.61
     fate
    -0.61
    MpServer
    -0.60
     Lazarus
    -0.60
    ilda
    -0.59
     Alm
    -0.59
     Crusade
    -0.59
    POSITIVE LOGITS
    due
    1.11
    taining
    1.07
    secut
    1.07
    ceived
    1.07
    ception
    1.05
    ceptions
    1.04
    manent
    1.02
    vasive
    0.98
    secution
    0.98
    missible
    0.97
    Activations Density 0.008%

    No Known Activations