© 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. 0-RES-JB
    6. 12207
    Prev
    Next
    INDEX
    Explanations

    phrases related to the material aluminum

    oai_token-act-pair · gpt-3.5-turbo

    references to aluminum and its properties

    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
     Feast
    -0.80
     Parties
    -0.74
    song
    -0.72
     Lords
    -0.71
    ivals
    -0.70
     endings
    -0.70
     Song
    -0.70
     Kingdoms
    -0.69
    Sexual
    -0.69
    Party
    -0.68
    POSITIVE LOGITS
     aluminum
    3.47
     aluminium
    3.09
     Aluminum
    2.94
    uminum
    2.47
     titanium
    2.22
     stainless
    1.94
    uminium
    1.94
     magnesium
    1.94
     alloy
    1.69
     steel
    1.68
    Activations Density 0.037%

    No Known Activations