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. 20285
    Prev
    Next
    INDEX
    Explanations

    phrases related to actively working on a task or project

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "working on."

    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
    Bey
    -0.81
    Champ
    -0.72
    few
    -0.70
    RL
    -0.70
    Override
    -0.69
    flies
    -0.65
    Jose
    -0.65
    ME
    -0.64
    YP
    -0.64
    Chel
    -0.63
    POSITIVE LOGITS
     behalf
    1.56
    eday
    0.99
     occasion
    0.82
     improving
    0.79
     developing
    0.78
    sets
    0.75
     impulse
    0.74
     ABE
    0.74
     Saturdays
    0.74
     preserving
    0.73
    Activations Density 0.089%

    No Known Activations