© 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. 4262
    Prev
    Next
    INDEX
    Explanations

    Phrases related to violations of rules or laws

    oai_token-act-pair · gpt-3.5-turbo

    terms related to violation of laws or rights

    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
    uther
    -0.71
    anka
    -0.71
    arger
    -0.70
    anol
    -0.70
    prototype
    -0.70
    onna
    -0.70
    cule
    -0.70
    apult
    -0.69
    ael
    -0.68
    affer
    -0.68
    POSITIVE LOGITS
     violations
    0.92
     unfocusedRange
    0.89
     violating
    0.89
     violation
    0.88
    viol
    0.83
     violates
    0.83
     infring
    0.78
     violated
    0.76
     violate
    0.75
     Viol
    0.71
    Activations Density 0.017%

    No Known Activations