© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 18928
    Prev
    Next
    INDEX
    Explanations

    terms related to violations of boundaries or rules, such as encroachment and trespassing

    oai_token-act-pair · gpt-3.5-turbo

    terms related to encroachment and trespassing

    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
     Tycoon
    -0.76
    axter
    -0.76
    hift
    -0.75
    ndra
    -0.73
    pace
    -0.69
    milo
    -0.69
    otine
    -0.69
    mith
    -0.68
     reconc
    -0.67
    saf
    -0.67
    POSITIVE LOGITS
     encro
    0.94
    rance
    0.82
     trespass
    0.80
     intr
    0.77
     Trafford
    0.75
     tresp
    0.74
     intrusion
    0.69
     patrols
    0.67
    glass
    0.67
    ursions
    0.66
    Activations Density 0.024%

    No Known Activations