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. 16443
    Prev
    Next
    INDEX
    Explanations

    names containing the substring "wan."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "Marwan"

    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
     liability
    -0.71
    ensed
    -0.69
     mileage
    -0.67
     clustered
    -0.67
    £ı
    -0.67
    İĭ
    -0.64
     leaflets
    -0.63
    ttle
    -0.63
     defiance
    -0.63
     imperative
    -0.63
    POSITIVE LOGITS
    igans
    1.08
     Kenobi
    1.03
    igan
    1.02
    hao
    1.01
    wan
    0.94
    loo
    0.94
    wu
    0.93
    artz
    0.90
    nee
    0.90
    ryu
    0.89
    Activations Density 0.012%

    No Known Activations