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. 6-RES-JB
    6. 16521
    Prev
    Next
    INDEX
    Explanations

    phrases related to working hard or putting in effort

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "worked hard."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NetMessage
    -0.67
    apter
    -0.66
     Kut
    -0.60
     Canad
    -0.60
     Dread
    -0.59
    ICAN
    -0.59
    ARDIS
    -0.59
    Sov
    -0.58
     Pau
    -0.58
     Nest
    -0.58
    POSITIVE LOGITS
    itud
    0.98
     enough
    0.81
    entimes
    0.78
     diligently
    0.78
     ahead
    0.77
    esley
    0.75
    working
    0.72
    enough
    0.71
     academ
    0.70
     hard
    0.69
    Activations Density 0.027%

    No Known Activations