© 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. 11-RES-JB
    11. 7637
    Prev
    Next
    INDEX
    Explanations

    Similar to Neuron 3, this neuron looks for phrases related to well-wishing and greetings

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating related content or references

    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
     arrang
    -0.88
    bably
    -0.82
     thereafter
    -0.82
    itionally
    -0.81
     carbohyd
    -0.80
    eatures
    -0.80
     tremend
    -0.80
    idine
    -0.79
     subsequently
    -0.77
     compositions
    -0.76
    POSITIVE LOGITS
     Why
    1.38
     How
    1.34
     Latest
    1.31
     Ranking
    1.21
     Meet
    1.20
     What
    1.17
     Where
    1.16
     Exclusive
    1.14
     Inside
    1.14
     Should
    1.13
    Activations Density 0.087%

    No Known Activations