© 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. 1279
    Prev
    Next
    INDEX
    Explanations

    locations and places

    oai_token-act-pair · gpt-3.5-turbo

    locations and geographical 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
    uploads
    -0.66
    abuse
    -0.65
    aped
    -0.64
     justifies
    -0.62
    thood
    -0.61
    Others
    -0.61
     overcame
    -0.61
     refuses
    -0.60
    emo
    -0.58
    calling
    -0.58
    POSITIVE LOGITS
     approximately
    0.79
     northeastern
    0.76
     mountainous
    0.74
     a
    0.73
     an
    0.73
     depths
    0.72
     northwestern
    0.72
     densely
    0.72
     Beir
    0.72
     roughly
    0.70
    Activations Density 0.280%

    No Known Activations