© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 10346
    Prev
    Next
    INDEX
    Explanations

    Filipino words and phrases

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to emotional expressions and complaints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enhagen
    -0.96
    NBA
    -0.91
    advertising
    -0.89
    ingham
    -0.88
    advertisement
    -0.88
    icks
    -0.86
    ickle
    -0.85
    below
    -0.84
    #$#$
    -0.84
    reads
    -0.84
    POSITIVE LOGITS
     la
    1.00
     lang
    0.88
     los
    0.85
     wal
    0.85
     bes
    0.85
     mand
    0.84
     kan
    0.83
     ber
    0.83
     pel
    0.83
     sar
    0.82
    Activations Density 0.096%

    No Known Activations