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. 11-RES-JB
    6. 3235
    Prev
    Next
    INDEX
    Explanations

    issues or problems related to technology

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating errors or issues with submissions and validations

    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
     Spotlight
    -0.58
    CTV
    -0.58
     Announce
    -0.55
     Curiosity
    -0.54
    terday
    -0.52
     alive
    -0.51
     Alive
    -0.51
    tein
    -0.50
     billboard
    -0.49
     Gaal
    -0.49
    POSITIVE LOGITS
    opers
    0.71
    ahs
    0.65
    orians
    0.61
    pport
    0.59
    orically
    0.58
    ople
    0.58
    use
    0.58
    ASON
    0.57
    oco
    0.56
    vol
    0.56
    Activations Density 0.331%

    No Known Activations