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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 18163
    Prev
    Next
    INDEX
    Explanations

    phrases related to someone's return to a particular activity or place

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "return."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Cola
    -0.75
    fusc
    -0.73
    hemat
    -0.72
    ascript
    -0.72
    cape
    -0.69
    vern
    -0.68
    bian
    -0.62
    mith
    -0.62
     Chocobo
    -0.62
    sonian
    -0.60
    POSITIVE LOGITS
    ees
    0.95
    home
    0.82
     home
    0.78
    Return
    0.77
     HOME
    0.76
     Returning
    0.75
    return
    0.75
    ends
    0.69
    backs
    0.67
     return
    0.66
    Activations Density 0.025%

    No Known Activations