© 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. 1566
    Prev
    Next
    INDEX
    Explanations

    specific mentions and discussions related to existing entities or structures

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "existing" and related concepts

    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
    aminer
    -0.85
    uchi
    -0.79
    alion
    -0.77
    76561
    -0.75
    ertodd
    -0.73
    asus
    -0.73
    rev
    -0.69
    ection
    -0.69
    arching
    -0.68
    10000
    -0.67
    POSITIVE LOGITS
     arrangements
    0.91
     ones
    0.88
     structures
    0.87
     relationships
    0.80
     precedent
    0.77
     patterns
    0.76
     systems
    0.76
     procedures
    0.75
     forms
    0.75
     frameworks
    0.75
    Activations Density 0.066%

    No Known Activations