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. 10493
    Prev
    Next
    INDEX
    Explanations

    specific phrases containing the term "hard-working"

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to hard work or dedication

    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
    ulhu
    -1.05
    çīĪ
    -0.77
    DragonMagazine
    -0.76
     Rica
    -0.73
    ADRA
    -0.73
     Noir
    -0.71
    ICAN
    -0.71
     guiActiveUn
    -0.71
    éŃĶ
    -0.70
     Creator
    -0.70
    POSITIVE LOGITS
    sounding
    1.30
    eyed
    1.22
    looking
    1.18
    sized
    1.15
    minded
    1.14
    hearted
    1.12
    issue
    1.09
    legged
    1.06
    shaped
    1.05
    numbered
    1.05
    Activations Density 0.128%

    No Known Activations