© 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 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. 11-RES-JB
    11. 17352
    Prev
    Next
    INDEX
    Explanations

    descriptions of violent actions or events

    oai_token-act-pair · gpt-3.5-turbo

    Quotes that describe events or actions with a strong emotional context

    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
     defic
    -0.96
     affili
    -0.88
     endeavors
    -0.87
     advoc
    -0.86
     innov
    -0.86
    ¥ŀ
    -0.84
     renew
    -0.83
     prosper
    -0.82
     distinguishing
    -0.81
     combating
    -0.81
    POSITIVE LOGITS
    Then
    1.46
     Then
    1.41
    Suddenly
    1.34
     Afterwards
    1.30
     Immediately
    1.24
     Suddenly
    1.23
     Didn
    1.23
     Somebody
    1.23
     Luckily
    1.21
    Eventually
    1.18
    Activations Density 0.278%

    No Known Activations