© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 8-RES-JB
    11. 10324
    Prev
    Next
    INDEX
    Explanations

    strings with characters "Ċ" and potentially other relevant symbols

    oai_token-act-pair · gpt-3.5-turbo

    instances of significant numeric values or identifiers in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Reincarnated
    -0.72
     aging
    -0.66
     ageing
    -0.66
    rad
    -0.66
     disillusion
    -0.62
    atis
    -0.62
     hust
    -0.62
     charm
    -0.61
     smack
    -0.60
    atche
    -0.59
    POSITIVE LOGITS
    Example
    1.00
    RESULTS
    0.95
    Important
    0.88
    NOTE
    0.87
    ³³³³³³³³³³³³³³³³
    0.85
    Learn
    0.82
    Examples
    0.80
    Additionally
    0.80
    TABLE
    0.80
    ³³³
    0.78
    Activations Density 0.437%

    No Known Activations