© 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. 8-RES-JB
    11. 8035
    Prev
    Next
    INDEX
    Explanations

    words related to "karma."

    oai_token-act-pair · gpt-3.5-turbo

    references to the letter 'K'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •words starting with k

    No Comments

    Negative Logits
    Ø©
    -0.71
    terday
    -0.70
     Malf
    -0.69
     chronological
    -0.67
     Murdoch
    -0.67
    IBLE
    -0.65
     expires
    -0.64
     TTL
    -0.64
     Staples
    -0.64
     unlaw
    -0.61
    POSITIVE LOGITS
    etchup
    1.31
    itty
    1.31
    idd
    1.26
    ansas
    1.18
    ratom
    1.18
    appa
    1.15
    idding
    1.14
    rieg
    1.09
    ippers
    1.08
    orea
    1.07
    Activations Density 0.029%

    No Known Activations