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

    Neuronpedia

    APICircuit 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. 6-RES-JB
    6. 16389
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases ending with a numeric unit followed by a punctuation mark

    oai_token-act-pair · gpt-3.5-turbo

    statements or facts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defe
    -0.72
     remission
    -0.71
     plasma
    -0.71
     corrections
    -0.69
     rod
    -0.68
     panc
    -0.68
     elbow
    -0.66
     clot
    -0.64
     silent
    -0.64
     punched
    -0.63
    POSITIVE LOGITS
     Additionally
    1.11
     Furthermore
    1.07
     Especially
    1.07
     Specifically
    1.07
     Particularly
    1.06
     Unfortunately
    1.04
     Moreover
    1.04
     Whereas
    1.04
     Ironically
    1.03
     Ultimately
    1.00
    Activations Density 0.689%

    No Known Activations