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. 21033
    Prev
    Next
    INDEX
    Explanations

    phrases related to describing, discussing, or outlining information

    oai_token-act-pair · gpt-3.5-turbo

    phrases that reference detailed descriptions or explanations

    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
     lasted
    -0.86
    ealous
    -0.68
     imperson
    -0.68
     reinstated
    -0.66
     overpowered
    -0.65
     recons
    -0.64
    acers
    -0.64
     persisted
    -0.64
    rio
    -0.63
     succeeded
    -0.63
    POSITIVE LOGITS
    effic
    0.93
     conjunction
    0.89
    appropriately
    0.84
    humane
    0.82
     parentheses
    0.81
    clus
    0.81
     order
    0.80
     advance
    0.79
    Quotes
    0.77
    ordinate
    0.76
    Activations Density 0.248%

    No Known Activations