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. 10369
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific scientific concept, likely related to particle physics

    oai_token-act-pair · gpt-3.5-turbo

    references to the Higgs boson and related terminology

    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
    ovie
    -0.66
    alities
    -0.65
    ahime
    -0.65
    ning
    -0.64
    icia
    -0.63
    exec
    -0.62
    ohydrate
    -0.60
    ography
    -0.60
    odor
    -0.60
    itia
    -0.59
    POSITIVE LOGITS
     bos
    1.05
    ource
    0.89
    loo
    0.86
    ertodd
    0.80
    iggs
    0.79
    olean
    0.75
     particle
    0.75
    boro
    0.73
     Ness
    0.71
    minster
    0.70
    Activations Density 0.017%

    No Known Activations