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. 11-RES-JB
    6. 8652
    Prev
    Next
    INDEX
    Explanations

    phrases indicating criticism or advice towards others

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "should" in various contexts related to suggestions and obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ends
    -0.66
     Fra
    -0.66
     Hilbert
    -0.64
    quickShipAvailable
    -0.63
     Dia
    -0.63
     Rox
    -0.62
    vous
    -0.60
    anka
    -0.60
     Oss
    -0.59
    atile
    -0.58
    POSITIVE LOGITS
    nt
    1.11
    ered
    1.09
     beware
    1.08
     ideally
    1.06
     be
    1.03
     aspire
    1.00
     strive
    0.99
     rethink
    0.99
     definitely
    0.98
     reconsider
    0.98
    Activations Density 0.107%

    No Known Activations