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. 8-RES-JB
    6. 19932
    Prev
    Next
    INDEX
    Explanations

    phrases related to rules, regulations, and arguments

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and transitional phrases in discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gleaming
    -0.80
    ORY
    -0.76
     Heads
    -0.74
     RAD
    -0.72
    iaries
    -0.70
    ORPG
    -0.69
     guiActiveUnfocused
    -0.68
    ories
    -0.67
    è¦ļéĨĴ
    -0.66
    ãĤ´ãĥ³
    -0.66
    POSITIVE LOGITS
     feas
    0.92
     alas
    0.86
     dare
    0.85
     somew
    0.84
    lege
    0.81
    necess
    0.81
    rouse
    0.80
     theoretically
    0.79
     someday
    0.78
     indeed
    0.77
    Activations Density 0.095%

    No Known Activations