© 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. 8345
    Prev
    Next
    INDEX
    Explanations

    terms related to chemical compounds or medical substances

    oai_token-act-pair · gpt-3.5-turbo

    terms related to amino acids and their derivatives

    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
     overrun
    -0.66
     enslaved
    -0.65
     Reach
    -0.65
     burst
    -0.65
     nest
    -0.64
     Territory
    -0.63
     split
    -0.63
     boasts
    -0.62
     surrounds
    -0.61
     borders
    -0.61
    POSITIVE LOGITS
    amin
    4.53
    amination
    2.34
    amina
    2.10
    amine
    1.91
    amines
    1.87
    amins
    1.81
    aminer
    1.58
    amen
    1.51
    ams
    1.45
    ami
    1.41
    Activations Density 0.008%

    No Known Activations