© 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. 9-RES-JB
    11. 10071
    Prev
    Next
    INDEX
    Explanations

    terms related to pedophilia and sexual misconduct

    oai_token-act-pair · gpt-3.5-turbo

    references to sexual offenses, particularly against minors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tune
    -0.82
     FORM
    -0.78
     shift
    -0.68
     Nun
    -0.68
     univers
    -0.68
     wisdom
    -0.68
     ISO
    -0.67
     bearer
    -0.66
     resemblance
    -0.66
     model
    -0.66
    POSITIVE LOGITS
    estation
    1.09
    assing
    1.07
    inations
    1.07
    inating
    1.07
    appings
    1.06
    ilings
    1.06
    acist
    1.05
    ocide
    1.02
    ination
    0.97
    ruption
    0.96
    Activations Density 0.132%

    No Known Activations