© 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. 9-RES-JB
    6. 2918
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical measurements or comparisons

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and directional phrases indicating movement or transition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unsu
    -0.63
     contagious
    -0.58
    Ĥª
    -0.58
     hijacked
    -0.58
     signs
    -0.55
     testim
    -0.55
     Pioneer
    -0.55
     signatures
    -0.53
     titles
    -0.53
     harmless
    -0.52
    POSITIVE LOGITS
    ilet
    1.42
    pping
    1.31
    pped
    1.25
    ppers
    1.07
    othy
    1.05
    ffee
    1.02
    ast
    1.00
    pper
    1.00
    oth
    0.99
    ppings
    0.94
    Activations Density 0.024%

    No Known Activations