© 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. 2-RES-JB
    11. 17642
    Prev
    Next
    INDEX
    Explanations

    words related to physical pulling or tugging

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "tug" and its related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mberg
    -0.74
    gow
    -0.70
    confidence
    -0.65
     Kuwait
    -0.65
    aghd
    -0.64
    iphate
    -0.64
     Expend
    -0.63
    Dub
    -0.63
    usage
    -0.63
     Hebdo
    -0.63
    POSITIVE LOGITS
    boat
    1.17
     tug
    1.14
    boats
    1.04
    ging
    1.03
    eteenth
    0.97
    ged
    0.97
    glers
    0.84
    ues
    0.80
    iculture
    0.76
    pole
    0.76
    Activations Density 0.008%

    No Known Activations