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. 7-RES-JB
    6. 4152
    Prev
    Next
    INDEX
    Explanations

    words related to cleansing or removing something

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "purge."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ONES
    -0.72
     Standing
    -0.71
     Unch
    -0.69
    areth
    -0.67
    lihood
    -0.65
    enegger
    -0.65
    olson
    -0.65
     Engel
    -0.64
     Werner
    -0.64
    LER
    -0.64
    POSITIVE LOGITS
    ple
    1.25
    vey
    1.21
    ported
    1.13
    ples
    1.08
    pose
    1.07
    porting
    1.05
    posed
    1.05
    poses
    1.03
    cell
    0.99
    pure
    0.99
    Activations Density 0.020%

    No Known Activations