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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-RES-JB
    6. 15678
    Prev
    Next
    INDEX
    Explanations

    quotations indicating someone speaking or saying something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating attribution or citation within scientific or academic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cffffcc
    -0.88
    anything
    -0.86
    à¼
    -0.78
    Offline
    -0.77
    usting
    -0.77
    ardless
    -0.77
    BRE
    -0.76
    ãĤ¦
    -0.73
    verage
    -0.71
    milo
    -0.71
    POSITIVE LOGITS
     researcher
    1.23
     study
    1.19
     Professor
    1.18
     Dr
    1.13
     researchers
    1.12
     biologist
    1.10
     Prof
    1.10
     lead
    1.07
     Canaver
    1.06
     Liang
    1.05
    Activations Density 0.116%

    No Known Activations