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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 0-RES-JB
    6. 5524
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical barriers or obstacles

    oai_token-act-pair · gpt-3.5-turbo

    references to gates or barriers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SHARE
    -0.80
     Schwarzenegger
    -0.69
    ornia
    -0.67
     Catalonia
    -0.66
    itus
    -0.65
     Nutrition
    -0.64
    enegger
    -0.64
    inen
    -0.63
    Share
    -0.62
    ivism
    -0.62
    POSITIVE LOGITS
     gate
    3.96
     gates
    3.04
     Gate
    2.47
    Gate
    1.99
     gateway
    1.94
    gate
    1.72
     door
    1.62
     Gateway
    1.43
     doors
    1.43
     Gates
    1.36
    Activations Density 0.016%

    No Known Activations