© 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. 4-RES-JB
    11. 912
    Prev
    Next
    INDEX
    Explanations

    terms related to legal compliance and adherence to rules

    oai_token-act-pair · gpt-3.5-turbo

    references to lawful behavior and adherence to rules

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

    No Comments

    Negative Logits
    oult
    -0.88
    ripp
    -0.85
    cair
    -0.84
    kill
    -0.79
    ammy
    -0.76
    hy
    -0.73
    paces
    -0.73
    nosis
    -0.71
    raped
    -0.70
    ilk
    -0.70
    POSITIVE LOGITS
    abiding
    1.13
     abiding
    1.01
     citizens
    0.80
     concealed
    0.78
     obe
    0.77
    tesy
    0.76
     citizen
    0.74
     ATF
    0.73
    ¿½
    0.71
    iciary
    0.71
    Activations Density 0.023%

    No Known Activations