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. 1-RES-JB
    6. 23469
    Prev
    Next
    INDEX
    Explanations

    phrases related to authenticity or credibility

    oai_token-act-pair · gpt-3.5-turbo

    terms indicating authenticity or truthfulness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    trap
    -0.74
     Slate
    -0.73
     Twins
    -0.71
     Cull
    -0.69
    Keys
    -0.68
     Sparrow
    -0.68
     Prism
    -0.66
     Marshal
    -0.66
     Daughter
    -0.65
     Orn
    -0.62
    POSITIVE LOGITS
     fide
    1.08
     bona
    0.98
     factual
    0.91
    ual
    0.89
    uine
    0.85
    ulty
    0.85
    oreal
    0.80
    iological
    0.77
     basis
    0.77
    ysical
    0.76
    Activations Density 0.025%

    No Known Activations