© 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. 9934
    Prev
    Next
    INDEX
    Explanations

    terms related to adult content or activities

    oai_token-act-pair · gpt-3.5-turbo

    references to adult industry-related terms and roles

    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
    adr
    -0.89
    atility
    -0.87
    ãĤ¡
    -0.84
    externalActionCode
    -0.76
    SOURCE
    -0.71
    pload
    -0.69
     Klux
    -0.68
    Ĥİ
    -0.68
    atile
    -0.68
    hops
    -0.67
    POSITIVE LOGITS
    erer
    1.10
     Swim
    1.05
    erers
    1.05
     males
    0.85
    ager
    0.85
     male
    0.84
    AGE
    0.81
     beverages
    0.81
    estate
    0.80
     supervision
    0.79
    Activations Density 0.031%

    No Known Activations