© 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. 22302
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "loaded"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "loaded" in various contexts

    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
    vention
    -0.73
    commun
    -0.71
     councils
    -0.71
     Rapp
    -0.69
     Entreprene
    -0.68
    icip
    -0.67
    see
    -0.66
    nm
    -0.66
     initiatives
    -0.66
     rapport
    -0.65
    POSITIVE LOGITS
     loaded
    3.72
    loaded
    2.30
     unloaded
    2.24
     Loaded
    2.07
     load
    1.80
     loading
    1.72
    Load
    1.69
    load
    1.60
    loading
    1.55
     loads
    1.54
    Activations Density 0.022%

    No Known Activations