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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 5-RES-JB
    6. 22616
    Prev
    Next
    INDEX
    Explanations

    words related to purification or cleansing

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "pur" and its variants related to purification or cleansing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Standing
    -0.81
    lihood
    -0.75
    enegger
    -0.68
     Stub
    -0.67
     Dragonbound
    -0.67
    ONES
    -0.66
     Unch
    -0.66
     Solitaire
    -0.64
     Half
    -0.63
    areth
    -0.62
    POSITIVE LOGITS
    ple
    1.13
    vey
    1.08
    posed
    1.04
    porting
    1.00
    ported
    0.97
    cell
    0.95
    fect
    0.95
    ples
    0.95
    pur
    0.94
    pling
    0.92
    Activations Density 0.010%

    No Known Activations