© 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. 22282
    Prev
    Next
    INDEX
    Explanations

    phrases related to hard work and dedication

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to hard work and struggle

    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
     guiActiveUn
    -1.02
    mbuds
    -0.75
    è¦ļéĨĴ
    -0.74
    assadors
    -0.74
    hig
    -0.72
    apor
    -0.71
    à¼
    -0.71
    minus
    -0.70
    66666666
    -0.69
    VERTIS
    -0.69
    POSITIVE LOGITS
    aiman
    0.67
     digestion
    0.65
    onica
    0.64
     brush
    0.64
     Alto
    0.63
     weeds
    0.61
     palate
    0.61
     tumble
    0.60
     abras
    0.60
     tofu
    0.60
    Activations Density 0.140%

    No Known Activations