© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 16851
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to things that are tempting or that provoke temptation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the words "tempt," "tempting," and "tempted."

    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
    iop
    -0.73
    ials
    -0.69
    internet
    -0.65
    stood
    -0.63
     Geneva
    -0.63
     Turbo
    -0.63
    riot
    -0.63
    LAN
    -0.62
    lining
    -0.62
     Glob
    -0.61
    POSITIVE LOGITS
     tempted
    1.32
     tempt
    1.31
     temptation
    1.22
     tempting
    1.11
    xtap
    0.89
     irresist
    0.86
     prey
    0.82
    terday
    0.82
     incent
    0.78
    uncture
    0.75
    Activations Density 0.008%

    No Known Activations