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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 3505
    Prev
    Next
    INDEX
    Explanations

    instances of legal terms or actions involving authorities

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to advocacy and support roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     inheritance
    -0.85
     snowball
    -0.71
    orno
    -0.68
     Decay
    -0.68
     celebration
    -0.65
    ¥µ
    -0.65
     Ruin
    -0.64
     stagn
    -0.64
     dissatisf
    -0.64
     crumbling
    -0.63
    POSITIVE LOGITS
     trained
    1.46
     tasked
    1.32
     hired
    1.27
     stationed
    1.25
     appointed
    1.25
     lia
    1.24
     superv
    1.24
     staffed
    1.21
    trained
    1.21
     liaison
    1.16
    Activations Density 0.558%

    No Known Activations