Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 19015
    Prev
    Next
    INDEX
    Explanations

    words related to stress and hectic situations

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "he"

    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
     aggregate
    -0.63
     internationally
    -0.60
     daytime
    -0.60
     Resolution
    -0.59
     worth
    -0.57
     flush
    -0.56
     interests
    -0.56
     firsthand
    -0.56
     futures
    -0.54
     Voltage
    -0.54
    POSITIVE LOGITS
    aping
    1.41
    uristic
    1.38
    redit
    1.35
    aped
    1.29
    ctic
    1.29
    ctor
    1.28
    ather
    1.25
    eded
    1.25
    irl
    1.24
    aps
    1.23
    Activations Density 0.069%

    No Known Activations