© 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. 9-RES-JB
    11. 10077
    Prev
    Next
    INDEX
    Explanations

    language related to overlooking or ignoring something

    oai_token-act-pair · gpt-3.5-turbo

    phrases and concepts related to neglecting or ignoring important issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icion
    -0.76
    ÃĥÃĤ
    -0.74
    TAIN
    -0.72
    abee
    -0.71
    icho
    -0.68
    ipop
    -0.66
    achus
    -0.66
     guiActive
    -0.65
    wik
    -0.65
    veyard
    -0.65
    POSITIVE LOGITS
     fact
    1.38
     realities
    1.37
     seriousness
    1.27
     significance
    1.23
     reality
    1.21
     importance
    1.19
     facts
    1.18
     inconvenient
    1.14
     possibility
    1.10
     complexities
    1.10
    Activations Density 0.367%

    No Known Activations