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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 10886
    Prev
    Next
    INDEX
    Explanations

    references to the magnitude of natural events or social impact

    oai_token-act-pair · gpt-3.5-turbo

    references to earthquake magnitudes

    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
    tek
    -0.77
    bones
    -0.74
    nee
    -0.73
    inelli
    -0.73
    azeera
    -0.72
    igslist
    -0.71
    croft
    -0.68
    ohydrate
    -0.68
    bies
    -0.68
    starter
    -0.68
    POSITIVE LOGITS
     magnitude
    1.15
     scale
    0.88
    externalActionCode
    0.82
     sensitivity
    0.80
     equival
    0.78
     iceberg
    0.77
     amplitude
    0.76
     submer
    0.75
     earthquake
    0.75
     è£ıè¦ļéĨĴ
    0.75
    Activations Density 0.018%

    No Known Activations