© 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. 3-RES-JB
    11. 3628
    Prev
    Next
    INDEX
    Explanations

    words related to enforcement or being enforced

    oai_token-act-pair · gpt-3.5-turbo

    terms related to enforcement and regulatory actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adra
    -0.84
    issues
    -0.82
    scribe
    -0.80
    umbn
    -0.78
    now
    -0.77
    adier
    -0.76
    cler
    -0.76
    ribe
    -0.76
    itte
    -0.76
    igmat
    -0.75
    POSITIVE LOGITS
     destro
    0.90
     inconsist
    0.82
     unintention
    0.78
    ãĤ´ãĥ³
    0.77
    DeliveryDate
    0.74
     exha
    0.74
     phased
    0.72
     intermitt
    0.71
    ieval
    0.69
     pione
    0.69
    Activations Density 0.058%

    No Known Activations