© 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. 11-RES-JB
    11. 20389
    Prev
    Next
    INDEX
    Explanations

    phrases related to inappropriate or offensive content

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to censorship and controversial content

    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
     patiently
    -0.84
     staggered
    -0.79
     waiting
    -0.76
     waits
    -0.75
    Luck
    -0.74
     luck
    -0.74
     Recovery
    -0.74
    kefeller
    -0.71
    ternity
    -0.71
    cells
    -0.71
    POSITIVE LOGITS
     objectionable
    1.44
     pornographic
    1.38
     derogatory
    1.37
     blasp
    1.34
     inciting
    1.30
     offend
    1.30
     provocative
    1.27
     indecent
    1.27
     disrespectful
    1.27
     nudity
    1.27
    Activations Density 0.757%

    No Known Activations