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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 4107
    Prev
    Next
    INDEX
    Explanations

    religious buildings or landmarks

    oai_token-act-pair · gpt-3.5-turbo

    references to cathedrals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    terness
    -0.91
    ilit
    -0.90
    bling
    -0.87
    union
    -0.83
    graph
    -0.83
    bles
    -0.82
    fits
    -0.81
    laus
    -0.80
    bell
    -0.80
    owship
    -0.80
    POSITIVE LOGITS
     Cathedral
    0.89
     Capitals
    0.70
     tabl
    0.68
     Clause
    0.67
     nursery
    0.66
     Hels
    0.66
     Divinity
    0.66
     Dawkins
    0.65
     envelope
    0.64
     PRESS
    0.63
    Activations Density 0.058%

    No Known Activations