© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 8-RES-JB
    11. 14125
    Prev
    Next
    INDEX
    Explanations

    phrases indicating concern about a negative event happening and the need to take action to prevent it

    oai_token-act-pair · gpt-3.5-turbo

    comparisons made using the phrase "like this" or "like that."

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     intermedi
    -0.67
    ionics
    -0.67
    WI
    -0.67
    itatively
    -0.66
    ione
    -0.65
    */(
    -0.64
     separately
    -0.63
     intermediate
    -0.63
    ools
    -0.61
    ESA
    -0.60
    POSITIVE LOGITS
     ours
    1.45
     hers
    1.33
     yours
    1.26
    lihood
    1.20
     theirs
    1.15
     mine
    0.85
    liest
    0.78
     Canaver
    0.78
    yip
    0.73
    luaj
    0.71
    Activations Density 0.155%

    No Known Activations