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. 9-RES-JB
    6. 663
    Prev
    Next
    INDEX
    Explanations

    phrases related to prices

    oai_token-act-pair · gpt-3.5-turbo

    repeated formatting elements or markers

    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
    rium
    -0.64
     bed
    -0.64
    croft
    -0.63
     localization
    -0.63
    lihood
    -0.63
     spirited
    -0.62
     LEG
    -0.61
     disappearing
    -0.60
     field
    -0.59
     loud
    -0.59
    POSITIVE LOGITS
    udence
    1.35
    atche
    1.15
    ussia
    1.10
    arie
    1.09
    imate
    1.09
    uning
    1.08
    imes
    1.07
    inter
    1.04
    ussian
    1.04
    ima
    1.03
    Activations Density 0.032%

    No Known Activations