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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 18818
    Prev
    Next
    INDEX
    Explanations

    instances where someone is speaking or quoting something

    oai_token-act-pair · gpt-3.5-turbo

    references to negative speech or statements made about others

    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
    Flickr
    -0.79
     Flickr
    -0.70
    edia
    -0.62
     Wikimedia
    -0.62
    ablished
    -0.62
     Mechanical
    -0.61
    lisher
    -0.61
     Flavoring
    -0.60
    ibal
    -0.59
    anding
    -0.59
    POSITIVE LOGITS
     aloud
    1.65
     loudly
    1.31
     goodbye
    1.23
     loud
    1.19
     louder
    1.04
     words
    0.96
     phrases
    0.93
     word
    0.92
     prayers
    0.92
    word
    0.92
    Activations Density 0.197%

    No Known Activations