© 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. 7-RES-JB
    11. 24001
    Prev
    Next
    INDEX
    Explanations

    phrases related to relaxation or break

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of rest or breaks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gee
    -0.67
    wered
    -0.62
     Mahjong
    -0.59
     twins
    -0.59
     undert
    -0.58
     tong
    -0.58
     Ear
    -0.57
     marriage
    -0.57
     combination
    -0.56
    GES
    -0.56
    POSITIVE LOGITS
    ructure
    1.25
    orative
    1.20
    raint
    1.07
    ock
    1.04
    ricted
    1.03
    ocking
    1.01
    ricting
    1.00
    raints
    1.00
    arts
    0.99
    oleon
    0.97
    Activations Density 0.014%

    No Known Activations