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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 7770
    Prev
    Next
    INDEX
    Explanations

    numerical values or measurements in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and metrics related to performance or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bung
    -0.60
     PVC
    -0.57
     Comet
    -0.55
    GMT
    -0.54
     ABV
    -0.54
     metic
    -0.54
     Pir
    -0.54
     Wilkinson
    -0.54
     Pengu
    -0.53
     Wik
    -0.53
    POSITIVE LOGITS
    ãĤ¤ãĥĪ
    0.61
    arser
    0.58
    èĥ
    0.55
    éĥ
    0.55
     versa
    0.55
     likewise
    0.55
     ones
    0.55
    ichen
    0.54
    oliath
    0.54
    åIJ
    0.54
    Activations Density 1.865%

    No Known Activations