© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 5562
    Prev
    Next
    INDEX
    Explanations

    the word "Real" followed by a capitalized word, potentially related to the Real Madrid football club

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Real" in various contexts, particularly in sports or entertainment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xual
    -0.80
    awk
    -0.73
     Sawyer
    -0.68
    URR
    -0.67
    EGIN
    -0.64
    \",
    -0.64
    ebook
    -0.63
     Whitman
    -0.62
    berries
    -0.60
     DRAG
    -0.59
    POSITIVE LOGITS
    ignment
    1.27
    istically
    1.10
    istic
    1.09
    igning
    1.08
     estate
    1.03
    estate
    1.02
    polit
    1.02
     Real
    1.02
     Estate
    1.01
    igned
    1.01
    Activations Density 0.007%

    No Known Activations