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. 7401
    Prev
    Next
    INDEX
    Explanations

    verbs related to communication and interaction

    oai_token-act-pair · gpt-3.5-turbo

    action verbs related to communication, collection, and destruction

    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
     halftime
    -0.64
     Parks
    -0.60
     HAL
    -0.60
     Aven
    -0.60
     Panthers
    -0.60
     Hurricanes
    -0.58
     Project
    -0.58
     Monument
    -0.58
     Reserve
    -0.58
     Provision
    -0.57
    POSITIVE LOGITS
    ings
    1.45
    ables
    1.42
    able
    1.39
    ers
    1.22
    ability
    1.21
    aways
    1.21
    ances
    1.21
    ancies
    1.21
    away
    1.15
    orship
    1.12
    Activations Density 0.295%

    No Known Activations