© 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. 7589
    Prev
    Next
    INDEX
    Explanations

    relationships in communication contexts, such as senders and recipients

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sending and receiving messages or communications

    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
     Pike
    -0.68
     Adventures
    -0.68
    enegger
    -0.66
    bsp
    -0.65
    romy
    -0.64
     Murd
    -0.63
     Revival
    -0.63
     Lethal
    -0.63
    ourning
    -0.62
    andise
    -0.61
    POSITIVE LOGITS
     beware
    1.05
    hip
    0.98
    paces
    0.94
     thereof
    0.87
     extraord
    0.81
    hips
    0.81
     Beware
    0.76
    itative
    0.74
    pace
    0.73
     alike
    0.72
    Activations Density 0.189%

    No Known Activations