© 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. 10-RES-JB
    11. 11598
    Prev
    Next
    INDEX
    Explanations

    references to window locations or paths in coding contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to web technologies and URLs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     squats
    -0.77
     mete
    -0.75
     ratios
    -0.74
     exponentially
    -0.74
     heavier
    -0.73
     oranges
    -0.72
     neut
    -0.70
     tigers
    -0.69
     blues
    -0.69
     poaching
    -0.68
    POSITIVE LOGITS
    Settings
    1.46
    Context
    1.45
    Attributes
    1.44
    Manager
    1.40
    Resource
    1.38
    Device
    1.38
    Config
    1.37
    Configuration
    1.36
    Interface
    1.36
    Enabled
    1.35
    Activations Density 0.188%

    No Known Activations