© 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. 1-RES-JB
    11. 18808
    Prev
    Next
    INDEX
    Explanations

    mentions of receiving or making phone calls

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "calls" indicating requests or communications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     concentration
    -0.68
     istg
    -0.67
     inh
    -0.66
     bunny
    -0.65
     Carth
    -0.64
    ositories
    -0.63
     coat
    -0.62
    inth
    -0.62
    Administ
    -0.62
     unden
    -0.62
    POSITIVE LOGITS
    call
    1.20
    backs
    1.18
     calls
    1.11
    calling
    0.92
     call
    0.91
    Call
    0.91
     Calling
    0.90
     Calls
    0.89
     calling
    0.88
     Niet
    0.87
    Activations Density 0.012%

    No Known Activations