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. 4-RES-JB
    6. 19244
    Prev
    Next
    INDEX
    Explanations

    phrases related to reducing or minimizing something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "cutting down."

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

    No Comments

    Negative Logits
     Jew
    -0.72
    tein
    -0.71
    cius
    -0.64
     disclaim
    -0.63
    owan
    -0.62
    jew
    -0.62
     Kenya
    -0.61
    WI
    -0.61
     �
    -0.60
     acqu
    -0.58
    POSITIVE LOGITS
    grading
    1.15
    stairs
    1.11
    graded
    1.05
    LOAD
    0.97
    pour
    0.89
     stairs
    0.89
    grades
    0.89
    regulation
    0.80
    baugh
    0.80
    hea
    0.76
    Activations Density 0.037%

    No Known Activations