© 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. 9-RES-JB
    11. 17659
    Prev
    Next
    INDEX
    Explanations

    instances where the text is predicting or discussing potential actions or outcomes

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express existence or presence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     TRUMP
    -0.70
    abases
    -0.67
     Bash
    -0.66
     Pants
    -0.64
     RG
    -0.62
     Uh
    -0.58
     Ada
    -0.58
    ogram
    -0.57
     MOR
    -0.57
    iffin
    -0.57
    POSITIVE LOGITS
     wont
    1.13
     attest
    1.03
     evidenced
    0.91
     deem
    0.77
     demonstrated
    0.76
     rightfully
    0.74
     often
    0.74
     deems
    0.72
     surely
    0.71
     witnessed
    0.71
    Activations Density 0.196%

    No Known Activations