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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 7-RES-JB
    6. 6565
    Prev
    Next
    INDEX
    Explanations

    references to toys, games, and play activities

    oai_token-act-pair · gpt-3.5-turbo

    references to play and recreational activities for children

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     copies
    -0.67
     thin
    -0.67
     defect
    -0.67
     firewall
    -0.65
     Diss
    -0.63
     scanned
    -0.63
    cloud
    -0.62
    ricanes
    -0.62
     leaks
    -0.62
    heed
    -0.61
    POSITIVE LOGITS
    ercise
    0.97
     pav
    0.87
    grounds
    0.85
    giving
    0.82
     routines
    0.79
    nels
    0.78
    wright
    0.77
    goers
    0.77
    cape
    0.75
    eers
    0.74
    Activations Density 0.221%

    No Known Activations