© 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. 8298
    Prev
    Next
    INDEX
    Explanations

    phrases related to controversies and scrutiny

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a sequence of events or consequences following certain actions

    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
    tick
    -0.76
    psy
    -0.75
    cin
    -0.74
    aez
    -0.74
    Typ
    -0.74
     isEnabled
    -0.74
    minus
    -0.74
    email
    -0.70
    Anyway
    -0.70
    achel
    -0.69
    POSITIVE LOGITS
     discovering
    1.00
     revelations
    0.92
     announcing
    0.89
     seeing
    0.89
     noticing
    0.85
     witnessing
    0.83
    words
    0.83
     failing
    0.82
    noon
    0.78
     repeated
    0.78
    Activations Density 0.104%

    No Known Activations