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. 10-RES-JB
    6. 23601
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions that involve performing steps or procedures

    oai_token-act-pair · gpt-3.5-turbo

    verbs that describe actions involving posting or sending information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lately
    -0.67
    BuyableInstoreAndOnline
    -0.66
     Too
    -0.61
    too
    -0.59
    undrum
    -0.59
     understatement
    -0.58
    than
    -0.58
     Shutterstock
    -0.56
     avoided
    -0.56
    avoid
    -0.55
    POSITIVE LOGITS
     accordingly
    1.03
     corresponding
    1.00
     thereafter
    0.99
     them
    0.96
     whichever
    0.95
     afterwards
    0.94
     subsequent
    0.93
     afterward
    0.87
     prest
    0.85
     resultant
    0.78
    Activations Density 0.601%

    No Known Activations