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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 9-RES-JB
    6. 731
    Prev
    Next
    INDEX
    Explanations

    instances where the concept of loyalty or faithfulness is mentioned

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing allegiance or loyalty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    llo
    -0.80
    TPPStreamerBot
    -0.70
    employed
    -0.69
    going
    -0.68
    ersed
    -0.68
    rio
    -0.67
     waived
    -0.65
     headed
    -0.65
    sky
    -0.64
     elig
    -0.64
    POSITIVE LOGITS
    wered
    0.92
     coincide
    0.89
     appease
    0.86
     ensure
    0.84
     conserve
    0.83
    ggles
    0.82
     signify
    0.82
    pless
    0.79
    days
    0.79
     minimize
    0.78
    Activations Density 0.262%

    No Known Activations