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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 22502
    Prev
    Next
    INDEX
    Explanations

    phrases related to a person or thing going back to a previous state or place

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of returning

    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
    arta
    -0.84
    ital
    -0.71
    Tube
    -0.68
    chn
    -0.68
    tec
    -0.68
    ean
    -0.67
    nih
    -0.66
    ismo
    -0.63
    oshop
    -0.62
    conom
    -0.62
    POSITIVE LOGITS
     returning
    3.51
     Returning
    2.62
     return
    1.99
     returned
    1.85
     returns
    1.81
     Return
    1.78
     departing
    1.76
    return
    1.72
    Return
    1.70
     exiting
    1.61
    Activations Density 0.008%

    No Known Activations