© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 4517
    Prev
    Next
    INDEX
    Explanations

    phrases related to things being physically full or crowded

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of being filled or packed tightly

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    externalActionCode
    -0.73
    appro
    -0.73
    APH
    -0.72
    relations
    -0.70
    grad
    -0.67
    EFF
    -0.66
    yer
    -0.65
    MAL
    -0.65
    mentioned
    -0.64
    KT
    -0.63
    POSITIVE LOGITS
     stuffed
    1.21
     stuffing
    0.97
    nesday
    0.94
    ulously
    0.86
    bag
    0.83
    bowl
    0.81
    bags
    0.80
    erton
    0.78
    ulous
    0.77
     bundles
    0.77
    Activations Density 0.008%

    No Known Activations