© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 7500
    Prev
    Next
    INDEX
    Explanations

    the word "different" in varying contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of being "different" or various forms of difference

    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
    OIL
    -0.62
     roundup
    -0.61
     PubMed
    -0.60
    ãĤ§
    -0.60
     Beans
    -0.59
    liner
    -0.58
     erection
    -0.58
    RF
    -0.58
    FL
    -0.56
     Palin
    -0.56
    POSITIVE LOGITS
    iating
    1.64
    iates
    1.44
    iated
    1.22
    iator
    1.20
    iations
    1.12
    ials
    1.04
    iable
    1.01
    ially
    0.99
    iate
    0.97
    iation
    0.96
    Activations Density 0.042%

    No Known Activations