© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 9350
    Prev
    Next
    INDEX
    Explanations

    phrases or topics related to size or scale

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "larger" in various contexts

    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
     Exile
    -0.77
    elf
    -0.73
    ocracy
    -0.73
    eline
    -0.72
    onso
    -0.70
     Bleach
    -0.70
    ILLE
    -0.69
     Called
    -0.68
    SR
    -0.67
     Yel
    -0.67
    POSITIVE LOGITS
     sized
    1.15
     intestine
    1.02
     than
    0.96
    than
    0.95
     eleph
    0.95
     quantities
    0.94
     diameter
    0.84
     scale
    0.80
     proport
    0.80
     carniv
    0.79
    Activations Density 0.012%

    No Known Activations