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. 3364
    Prev
    Next
    INDEX
    Explanations

    references to various types of play activities

    oai_token-act-pair · gpt-3.5-turbo

    activities related to children's play

    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
     Diss
    -0.70
    ãĥīãĥ©ãĤ´ãĥ³
    -0.67
    ricanes
    -0.64
     veins
    -0.62
    ought
    -0.60
     firewall
    -0.59
    ãĥĥãĥī
    -0.58
     levers
    -0.58
    çĶ
    -0.58
    ioxide
    -0.58
    POSITIVE LOGITS
    ercise
    0.93
    atorium
    0.88
    grounds
    0.85
     pian
    0.82
    ctor
    0.81
    wright
    0.81
     Piano
    0.77
     playground
    0.76
     Circus
    0.76
    glers
    0.75
    Activations Density 0.147%

    No Known Activations