© 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. 1-RES-JB
    11. 14135
    Prev
    Next
    INDEX
    Explanations

    terms related to seduction and related actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to seduction and illicit behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pei
    -0.82
    Universal
    -0.69
     Organisation
    -0.68
    Aren
    -0.68
    unknown
    -0.68
    Unknown
    -0.66
     Origin
    -0.66
    credit
    -0.65
    FG
    -0.64
    ONES
    -0.62
    POSITIVE LOGITS
     sed
    1.30
    iments
    1.12
    entary
    1.10
    uctive
    1.03
     Sed
    0.99
    sed
    0.92
    uces
    0.91
    uct
    0.91
    imentary
    0.88
     incent
    0.84
    Activations Density 0.008%

    No Known Activations