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. 2-RES-JB
    6. 13105
    Prev
    Next
    INDEX
    Explanations

    physical actions and propositions involving knowledge or awareness

    oai_token-act-pair · gpt-3.5-turbo

    the usage of the phrase "you know" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Development
    -0.78
    Bridge
    -0.68
    Engineers
    -0.68
    Init
    -0.67
    Els
    -0.66
    Applic
    -0.66
    Emer
    -0.65
    Whe
    -0.64
    Aren
    -0.64
    Apps
    -0.64
    POSITIVE LOGITS
     yourself
    1.03
     yourselves
    1.01
     lucky
    0.74
     your
    0.74
    ogie
    0.69
    neau
    0.67
    merce
    0.66
     panties
    0.66
     SAY
    0.65
     bathing
    0.65
    Activations Density 0.981%

    No Known Activations