© 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. 0-RES-JB
    11. 8218
    Prev
    Next
    INDEX
    Explanations

    measurements or technical details

    oai_token-act-pair · gpt-3.5-turbo

    the presence of special symbols or characters, specifically "ÃĹ"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     �
    -1.00
     ''
    -0.91
     ``
    -0.74
     Prescott
    -0.73
     Frankfurt
    -0.69
     Directorate
    -0.62
     deferred
    -0.62
     Tobacco
    -0.62
    oration
    -0.61
     ....
    -0.61
    POSITIVE LOGITS
    ÃĹ
    3.61
    âĢ³
    1.31
    x
    1.24
    xb
    1.02
    âĢ²
    1.01
    Advertisements
    0.96
    xff
    0.95
    ±
    0.94
    xd
    0.94
    Untitled
    0.91
    Activations Density 0.009%

    No Known Activations