© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 10202
    Prev
    Next
    INDEX
    Explanations

    credit-related words and phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to credit and credit-related terms

    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
     Osw
    -0.75
     Lans
    -0.74
     Bei
    -0.73
     Wem
    -0.71
    vae
    -0.69
     Reborn
    -0.64
    xon
    -0.64
     Kus
    -0.64
    xy
    -0.63
    ++++++++
    -0.63
    POSITIVE LOGITS
     card
    1.01
    card
    1.01
    worthiness
    0.96
    enza
    0.95
     CARD
    0.94
    worthy
    0.92
    cards
    0.86
    Card
    0.86
     lender
    0.84
     cards
    0.82
    Activations Density 0.012%

    No Known Activations