© 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. 1-RES-JB
    11. 13428
    Prev
    Next
    INDEX
    Explanations

    mentions of the concept of "returning" or going back to a previous state or location

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "returning"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hemat
    -0.87
    ascript
    -0.86
    chen
    -0.74
    phabet
    -0.69
    ulence
    -0.68
    Cola
    -0.67
    elo
    -0.67
    chie
    -0.66
    fusc
    -0.66
    berra
    -0.64
    POSITIVE LOGITS
     Returning
    0.97
     returning
    0.83
    Return
    0.78
     returns
    0.72
     returned
    0.71
    interstitial
    0.70
     Returns
    0.68
    return
    0.68
    earchers
    0.65
     return
    0.65
    Activations Density 0.005%

    No Known Activations