© 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. 4-RES-JB
    11. 11089
    Prev
    Next
    INDEX
    Explanations

    non-alphabetical characters and symbols

    oai_token-act-pair · gpt-3.5-turbo

    instances of significant numerical values or metrics related to processes or conditions

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

    No Comments

    Negative Logits
     hust
    -0.71
     lifes
    -0.70
     Aval
    -0.69
     receiving
    -0.63
    heit
    -0.62
    utics
    -0.61
     seeking
    -0.59
    utic
    -0.59
     undet
    -0.58
     urge
    -0.57
    POSITIVE LOGITS
    Conclusion
    1.10
    Furthermore
    0.98
    CONCLUS
    0.98
    Therefore
    0.96
    Likewise
    0.95
    Example
    0.94
    Advertisements
    0.94
    Lastly
    0.93
    Interestingly
    0.92
    Thus
    0.92
    Activations Density 1.044%

    No Known Activations