© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2824
    Prev
    Next
    INDEX
    Explanations

    words with the root "kn" followed by a vowel or rasping sound

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "kn" and its variations in different contexts

    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
    href
    -0.81
    atar
    -0.72
    amation
    -0.70
     Hulk
    -0.70
    ](
    -0.69
    enium
    -0.69
     Saban
    -0.66
     Morales
    -0.66
     Incredible
    -0.65
    soDeliveryDate
    -0.64
    POSITIVE LOGITS
     kn
    3.88
     Kn
    1.92
    kn
    1.79
    Kn
    1.70
     kne
    1.54
     knit
    1.53
     knob
    1.50
     KN
    1.44
     knitting
    1.37
    KN
    1.35
    Activations Density 0.018%

    No Known Activations