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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 8436
    Prev
    Next
    INDEX
    Explanations

    keywords related to tools and toolkits

    oai_token-act-pair · gpt-3.5-turbo

    references to tools and tool-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
     Sons
    -0.85
     charact
    -0.66
    egal
    -0.65
     sons
    -0.65
     Winds
    -0.64
    ilipp
    -0.64
    ospons
    -0.62
     twins
    -0.60
     Bom
    -0.60
     iod
    -0.56
    POSITIVE LOGITS
    kit
    1.74
    tips
    1.55
    tip
    1.35
    box
    1.31
    chain
    1.27
    belt
    1.21
    sonian
    1.14
    boxes
    1.14
    set
    1.12
    chains
    1.07
    Activations Density 0.055%

    No Known Activations