© 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. 4-RES-JB
    11. 7232
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific entity called "Lab"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Lab" followed by a number, indicating references to specific laboratories

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

    No Comments

    Negative Logits
     odds
    -0.80
    theless
    -0.78
     Marketable
    -0.78
    DIT
    -0.71
     understatement
    -0.70
    FUL
    -0.65
     LAST
    -0.62
    MENT
    -0.62
     Oaks
    -0.62
    å¹
    -0.62
    POSITIVE LOGITS
    yrinth
    1.38
    orers
    1.14
    rador
    1.14
    eled
    1.04
    elled
    1.04
    els
    1.01
    VIEW
    0.94
    emark
    0.89
    eling
    0.87
    rum
    0.85
    Activations Density 0.013%

    No Known Activations