© 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. 8-RES-JB
    6. 6276
    Prev
    Next
    INDEX
    Explanations

    names related to "Kl" with increasing activation values

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Kl" and its variations

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.75
    Interstitial
    -0.74
    CLASSIFIED
    -0.72
    EMENT
    -0.72
    ãģ®éŃĶ
    -0.69
     Thumbnails
    -0.69
     spirited
    -0.66
    LEASE
    -0.64
    ded
    -0.64
     quo
    -0.64
    POSITIVE LOGITS
    assic
    1.28
    utz
    1.15
    itsch
    1.14
    avier
    1.11
    oser
    1.11
    adium
    1.07
    osing
    1.06
    utch
    1.05
    avan
    1.03
    aston
    1.02
    Activations Density 0.020%

    No Known Activations