© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 13820
    Prev
    Next
    INDEX
    Explanations

    phrases related to illegal activities involving children

    oai_token-act-pair · gpt-3.5-turbo

    mentions of child-related offenses and abuses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bullets
    -0.83
    atility
    -0.82
    CRIP
    -0.75
    olulu
    -0.72
    href
    -0.69
    mith
    -0.66
    ä½ľ
    -0.64
    aeda
    -0.64
    使
    -0.63
    daq
    -0.62
    POSITIVE LOGITS
    ishly
    1.06
    bearing
    0.98
    child
    0.90
    birth
    0.88
    hood
    0.88
    children
    0.87
    olester
    0.83
    girls
    0.82
    girl
    0.81
    killer
    0.78
    Activations Density 0.031%

    No Known Activations