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. 23103
    Prev
    Next
    INDEX
    Explanations

    phrases related to the ability or action of doing something

    oai_token-act-pair · gpt-3.5-turbo

    statements expressing potential or capability

    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
    ccording
    -0.64
    DERR
    -0.64
     insofar
    -0.62
     Coff
    -0.60
     surn
    -0.60
     Hits
    -0.59
     Wrong
    -0.58
     Seeking
    -0.58
    cens
    -0.58
     Sack
    -0.58
    POSITIVE LOGITS
    't
    1.38
     afford
    1.23
     confidently
    1.10
     safely
    1.09
     easily
    1.05
     concentrate
    1.05
     continue
    0.99
     comfortably
    0.99
     enjoy
    0.95
     proceed
    0.94
    Activations Density 0.135%

    No Known Activations