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. 0-RES-JB
    6. 8465
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or entities

    oai_token-act-pair · gpt-3.5-turbo

    the term "Trinity" or related references to institutions or concepts involving the Trinity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     scratched
    -0.77
     scratch
    -0.72
     pengu
    -0.70
     scratches
    -0.69
     depress
    -0.66
    idates
    -0.65
    van
    -0.63
    che
    -0.63
     revol
    -0.61
    bal
    -0.60
    POSITIVE LOGITS
     Trinity
    4.04
     Trin
    1.50
     Divinity
    1.46
     Corpus
    1.25
     Sacrament
    1.24
     Dominion
    1.15
     Niagara
    1.14
     Catalyst
    1.11
     Resurrection
    1.06
     Thames
    1.05
    Activations Density 0.024%

    No Known Activations