© 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 EvalsExportsinterp-engineNEWAPI 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. 0-RES-JB
    11. 15371
    Prev
    Next
    INDEX
    Explanations

    references to the act of sacking or being sacked in a football context

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "sack" in various contexts, particularly in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XY
    -0.75
     Phant
    -0.72
    live
    -0.65
    location
    -0.65
     affiliates
    -0.65
    Mod
    -0.64
     Live
    -0.64
     Flor
    -0.63
    Link
    -0.63
     Theme
    -0.62
    POSITIVE LOGITS
     sack
    3.81
     sacks
    3.80
     Sack
    2.11
     sacked
    1.65
     interceptions
    1.17
     rusher
    1.13
     tackles
    1.03
     linebackers
    1.01
     lineback
    1.00
     interception
    0.99
    Activations Density 0.019%

    No Known Activations