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. 8594
    Prev
    Next
    INDEX
    Explanations

    numbers and codes

    oai_token-act-pair · gpt-3.5-turbo

    instances of numerical data or statistics related to events or circumstances

    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
     eleph
    -0.88
     neighbouring
    -0.85
     spir
    -0.81
     shelling
    -0.79
    ortunately
    -0.78
     neighboring
    -0.78
     resulting
    -0.77
     regener
    -0.75
     citiz
    -0.74
     servic
    -0.74
    POSITIVE LOGITS
    First
    1.63
    1
    1.62
    Firstly
    1.62
    Introduction
    1.56
    Myth
    1.49
    PART
    1.47
    FIR
    1.47
    Continue
    1.47
    Overview
    1.47
    THE
    1.46
    Activations Density 0.276%

    No Known Activations