Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 9783
    Prev
    Next
    INDEX
    Explanations

    words related to a specific name "Kl"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Kl" followed by varying contexts, likely related to specific individuals or characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Civic
    -0.66
     literacy
    -0.65
     ratings
    -0.63
     Elena
    -0.61
     plural
    -0.60
    CLASSIFIED
    -0.60
     mant
    -0.60
     quo
    -0.60
     safely
    -0.59
     FANTASY
    -0.59
    POSITIVE LOGITS
    assic
    1.41
    avier
    1.31
    itsch
    1.29
    utch
    1.21
    utz
    1.18
    oser
    1.15
    oves
    1.14
    oss
    1.09
    ubb
    1.09
    ug
    1.08
    Activations Density 0.030%

    No Known Activations