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. 10-RES-JB
    6. 21113
    Prev
    Next
    INDEX
    Explanations

    personal possessive pronouns

    oai_token-act-pair · gpt-3.5-turbo

    first-person references in the context of online blogs or personal narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SHAR
    -0.88
     Irving
    -0.85
    rir
    -0.82
    Rh
    -0.80
     Ruler
    -0.79
    rain
    -0.78
     Vand
    -0.78
    Ir
    -0.76
    isl
    -0.76
     Sins
    -0.75
    POSITIVE LOGITS
     Blog
    1.42
     blog
    1.37
    blog
    1.34
    Blog
    1.28
     blogs
    1.22
     blogging
    1.14
     blogger
    1.10
     bloggers
    1.08
    blogs
    1.06
    Camp
    1.02
    Activations Density 0.260%

    No Known Activations