Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-RES-JB
    6. 7694
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences indicating a topic is being discussed or brought up for consideration

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "raise" along with discussions of related issues or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nar
    -0.72
    destruct
    -0.70
     Antar
    -0.66
    sbm
    -0.66
    flix
    -0.65
    ãĤ´ãĥ³
    -0.64
    kered
    -0.63
    semb
    -0.62
    tery
    -0.60
    dest
    -0.60
    POSITIVE LOGITS
     eyebrows
    1.32
     stakes
    1.07
     eyebrow
    1.06
     profile
    0.98
     ante
    0.96
     threshold
    0.92
     ire
    0.91
     awareness
    0.90
     curtain
    0.89
     prices
    0.89
    Activations Density 0.106%

    No Known Activations