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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11-RES-JB
    11. 2003
    Prev
    Next
    INDEX
    Explanations

    instances where numbers, percentages, or codes are mentioned

    oai_token-act-pair · gpt-3.5-turbo

    significant declarative statements or claims about facts or statistics

    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
    EStream
    -0.61
    Þ
    -0.61
     exting
    -0.58
     practition
    -0.55
     pione
    -0.55
    StreamerBot
    -0.53
    REDACTED
    -0.53
    âķIJ
    -0.52
     eleph
    -0.51
    aditional
    -0.50
    POSITIVE LOGITS
     hers
    0.46
     Sometimes
    0.45
     Picks
    0.41
     sometimes
    0.41
    olds
    0.40
     others
    0.39
     Enemies
    0.39
    sometimes
    0.39
     But
    0.39
     Dems
    0.38
    Activations Density 1.459%

    No Known Activations