© 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. 6-RES-JB
    6. 15234
    Prev
    Next
    INDEX
    Explanations

    words ending in `'s'

    oai_token-act-pair · gpt-3.5-turbo

    the word "is" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     coff
    -0.61
     pots
    -0.61
     itiner
    -0.60
     resent
    -0.59
     schedules
    -0.56
     resorts
    -0.53
     organizing
    -0.53
     Pharaoh
    -0.53
     masses
    -0.53
     Spani
    -0.53
    POSITIVE LOGITS
    lightly
    0.84
    ELF
    0.83
    ustainable
    0.80
    wered
    0.80
    nown
    0.78
    mean
    0.78
    aurus
    0.76
    por
    0.75
    ought
    0.73
    Bio
    0.73
    Activations Density 0.041%

    No Known Activations