© 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. 3-RES-JB
    11. 23372
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and concepts, mainly focusing on defining and declaring

    oai_token-act-pair · gpt-3.5-turbo

    programming and coding-related terminology, specifically focusing on definitions and declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bill
    -0.99
    76561
    -0.97
    fare
    -0.88
    abouts
    -0.84
    Crunch
    -0.81
    edin
    -0.75
    é¾įå
    -0.75
    peria
    -0.73
    é¾įå¥ij士
    -0.72
    shoot
    -0.72
    POSITIVE LOGITS
     syntax
    0.97
     sandbox
    0.85
     java
    0.84
     bindings
    0.84
     namespace
    0.84
     commands
    0.82
     defaults
    0.82
     deprecated
    0.81
     exported
    0.80
     Container
    0.79
    Activations Density 0.079%

    No Known Activations