© 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. 2-RES-JB
    11. 22564
    Prev
    Next
    INDEX
    Explanations

    terms related to the act of penetration or infiltration

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of penetration

    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
    Lot
    -0.73
    HCR
    -0.68
    quickShipAvailable
    -0.67
     fork
    -0.65
    umble
    -0.64
     Malf
    -0.62
    nesota
    -0.61
     Scand
    -0.60
    aver
    -0.58
     Vale
    -0.58
    POSITIVE LOGITS
     penet
    1.40
     penetration
    1.36
     penetrated
    1.36
     penetrate
    1.35
     penetrating
    1.13
     Penet
    0.98
     pierced
    0.80
    latable
    0.78
    ierce
    0.78
    ensibly
    0.77
    Activations Density 0.009%

    No Known Activations