© 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. 3458
    Prev
    Next
    INDEX
    Explanations

    accounts of overcoming fear and challenges

    oai_token-act-pair · gpt-3.5-turbo

    emotional responses and experiences during stressful situations

    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
    igmat
    -0.72
     duplication
    -0.64
     detrim
    -0.61
     disse
    -0.60
     Distance
    -0.60
    ãĤ®
    -0.60
    lag
    -0.59
     Catalog
    -0.59
    agram
    -0.59
    igate
    -0.58
    POSITIVE LOGITS
     nonetheless
    1.53
     nevertheless
    1.45
     regained
    1.25
     survived
    1.25
     persisted
    1.25
     fortunately
    1.22
     luckily
    1.19
     recovered
    1.15
     managed
    1.14
     thankfully
    1.13
    Activations Density 0.398%

    No Known Activations