© 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. 10-RES-JB
    11. 18566
    Prev
    Next
    INDEX
    Explanations

    materials or substances that something is made from

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the source or material from which something is made

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Enlarge
    -0.73
    IRC
    -0.72
    bernatorial
    -0.72
    akia
    -0.70
     behav
    -0.69
    akings
    -0.69
    gencies
    -0.68
    Http
    -0.68
    hai
    -0.68
    Lens
    -0.68
    POSITIVE LOGITS
     scratch
    1.54
     recycled
    1.27
     scraps
    1.22
     reclaimed
    1.07
     salv
    1.05
     materials
    1.02
     pure
    1.01
     wood
    1.00
     discarded
    0.95
     leftover
    0.94
    Activations Density 0.133%

    No Known Activations