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

    Neuronpedia

    Jacobian LensNEW
    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. 1-RES-JB
    11. 21571
    Prev
    Next
    INDEX
    Explanations

    phrases related to hard work, perseverance, and enduring difficult circumstances

    oai_token-act-pair · gpt-3.5-turbo

    references to hard work or persistence, often in the context of struggle or effort

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    por
    -0.70
     caption
    -0.64
    uana
    -0.64
    PRES
    -0.63
    tymology
    -0.62
     Nations
    -0.60
    cept
    -0.59
    acl
    -0.59
    amera
    -0.58
     Christ
    -0.58
    POSITIVE LOGITS
     grind
    1.28
     Grind
    0.96
     grinding
    0.87
    ingly
    0.87
    stone
    0.82
    sheet
    0.74
    stones
    0.73
     è£ıè
    0.73
    itudinal
    0.73
    aign
    0.73
    Activations Density 0.007%

    No Known Activations