© 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. 11-RES-JB
    11. 16740
    Prev
    Next
    INDEX
    Explanations

    words related to the term "loyalty"

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "loy" and its variations in relation to various contexts

    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
     reuse
    -0.60
    igion
    -0.59
    itous
    -0.59
     needles
    -0.59
     ISI
    -0.57
     paternity
    -0.56
    ++++
    -0.55
     Zeit
    -0.55
    isable
    -0.55
    icably
    -0.55
    POSITIVE LOGITS
    nih
    1.27
    alties
    1.07
    eon
    1.06
    tek
    1.03
    enne
    1.01
    annis
    1.01
    eur
    1.00
    aml
    0.93
    ds
    0.91
    eah
    0.91
    Activations Density 0.075%

    No Known Activations