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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 2727
    Prev
    Next
    INDEX
    Explanations

    phrases related to loading or unloading of items or information

    oai_token-act-pair · gpt-3.5-turbo

    terms related to loading and the capacity of systems or processes

    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
     pet
    -0.69
     cond
    -0.67
     desired
    -0.67
     imperson
    -0.64
     ob
    -0.64
     professional
    -0.63
     idol
    -0.63
     jud
    -0.63
     styl
    -0.63
     cur
    -0.62
    POSITIVE LOGITS
    load
    4.37
    loads
    3.77
    loading
    3.24
    loaded
    2.80
    LOAD
    2.33
    loader
    2.17
    Load
    1.76
     Load
    1.51
     load
    1.48
     loads
    1.36
    Activations Density 0.017%

    No Known Activations