Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 2659
    Prev
    Next
    INDEX
    Explanations

    terms related to criminal activities involving children

    oai_token-act-pair · gpt-3.5-turbo

    references to children in the context of serious criminal offenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atility
    -0.81
    olulu
    -0.76
     Bullets
    -0.75
    CRIP
    -0.71
    aukee
    -0.65
    aeda
    -0.65
    auga
    -0.64
    ä½ľ
    -0.62
    mith
    -0.62
     plurality
    -0.62
    POSITIVE LOGITS
    ishly
    1.04
    bearing
    1.00
    birth
    0.94
    hood
    0.91
    children
    0.81
    child
    0.80
    killer
    0.78
    olester
    0.78
     conceived
    0.75
    riages
    0.74
    Activations Density 0.035%

    No Known Activations