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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 11216
    Prev
    Next
    INDEX
    Explanations

    verbs related to encouraging and promoting actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating encouragement or motivation

    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
    _.
    -0.68
     Recorded
    -0.64
     Illustrated
    -0.61
    anchester
    -0.60
    quickShipAvailable
    -0.60
     coefficients
    -0.58
    HTTP
    -0.57
    oslov
    -0.56
     Spoiler
    -0.55
     Appears
    -0.55
    POSITIVE LOGITS
     pursue
    1.07
     participate
    1.05
     embrace
    0.98
     emulate
    0.98
     undertake
    0.97
     explore
    0.97
     enroll
    0.96
     donate
    0.96
     avoid
    0.95
     join
    0.95
    Activations Density 0.154%

    No Known Activations