© 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. 8-RES-JB
    11. 3164
    Prev
    Next
    INDEX
    Explanations

    phrases related to hard work or effort

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of hard work

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     guiActiveUn
    -0.73
    66666666
    -0.65
     Burk
    -0.64
     istg
    -0.64
    EMENT
    -0.62
    ULAR
    -0.62
    ivo
    -0.61
     Cah
    -0.61
     existence
    -0.60
     absurdity
    -0.60
    POSITIVE LOGITS
    hitting
    1.26
    coded
    1.11
    won
    1.05
    earned
    1.01
    pressed
    0.97
    stem
    0.93
    bodied
    0.92
    charging
    0.91
    edged
    0.90
    hearted
    0.90
    Activations Density 0.052%

    No Known Activations