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. 11-RES-JB
    6. 10480
    Prev
    Next
    INDEX
    Explanations

    types of fans related to various interests or hobbies

    oai_token-act-pair · gpt-3.5-turbo

    references to specific fandoms and related cultural interests

    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
     Substance
    -0.69
    shown
    -0.69
    ructure
    -0.68
     jointly
    -0.67
     Thames
    -0.66
     FEC
    -0.65
     CrossRef
    -0.64
     Completed
    -0.64
     LIMITED
    -0.63
     electronically
    -0.63
    POSITIVE LOGITS
     enthusiasts
    1.63
     lovers
    1.53
     fans
    1.52
     wat
    1.38
     buffs
    1.36
     enthusiast
    1.36
     devote
    1.36
     nerds
    1.35
     supporters
    1.33
     believers
    1.30
    Activations Density 0.409%

    No Known Activations