© 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. 10-RES-JB
    11. 9969
    Prev
    Next
    INDEX
    Explanations

    phrases indicating an action or purpose

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating purpose or intention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Typ
    -0.75
    wrote
    -0.70
    writ
    -0.69
     Printed
    -0.66
     snipp
    -0.66
     Steps
    -0.66
    loads
    -0.64
    said
    -0.62
     Orange
    -0.61
    prints
    -0.61
    POSITIVE LOGITS
     maximize
    1.51
     minimize
    1.50
     avoid
    1.42
     preserve
    1.41
     conserve
    1.40
     lessen
    1.37
     appease
    1.31
     facilitate
    1.31
     prevent
    1.26
     regain
    1.24
    Activations Density 0.155%

    No Known Activations