© 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. 7-RES-JB
    11. 1807
    Prev
    Next
    INDEX
    Explanations

    questions in a structured format with specific keywords

    oai_token-act-pair · gpt-3.5-turbo

    questions and context brackets commonly used in dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oche
    -0.81
    formed
    -0.70
    ãĤ§
    -0.68
    igans
    -0.64
    itol
    -0.63
    rawdownloadcloneembedreportprint
    -0.63
    ahime
    -0.63
     Revel
    -0.61
    Constructed
    -0.60
    comb
    -0.60
    POSITIVE LOGITS
     Explain
    1.01
     Whats
    0.84
     Lastly
    0.77
     Would
    0.77
     Did
    0.76
     Could
    0.76
     Does
    0.76
    How
    0.76
     How
    0.74
     WHAT
    0.74
    Activations Density 0.121%

    No Known Activations