© 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. 20059
    Prev
    Next
    INDEX
    Explanations

    words related to dynamism, movement or change

    oai_token-act-pair · gpt-3.5-turbo

    references to dynamic changes or events

    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
     Answers
    -0.75
    boro
    -0.75
    lled
    -0.74
     anus
    -0.71
    bay
    -0.71
     Hallow
    -0.70
     Pur
    -0.70
    tin
    -0.69
     Pis
    -0.68
    berries
    -0.68
    POSITIVE LOGITS
     dynamic
    3.55
     Dynamic
    2.60
    Dynamic
    2.38
    ynamic
    1.99
     dynamically
    1.96
     dynamics
    1.87
     static
    1.53
     dynam
    1.29
     Static
    1.28
     statically
    1.24
    Activations Density 0.020%

    No Known Activations