© 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 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. 10-RES-JB
    11. 3292
    Prev
    Next
    INDEX
    Explanations

    instances of words related to the action of "returning"

    oai_token-act-pair · gpt-3.5-turbo

    references to the act of returning or coming back

    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
    ussen
    -0.73
    inen
    -0.72
    ghai
    -0.71
    stood
    -0.64
    bis
    -0.64
     Contra
    -0.61
    iop
    -0.59
    vern
    -0.59
    Cola
    -0.58
    ulhu
    -0.58
    POSITIVE LOGITS
     home
    1.14
    ees
    0.98
     HOME
    0.94
     to
    0.86
    home
    0.82
     victorious
    0.76
     safely
    0.75
     whence
    0.73
     intact
    0.70
     Home
    0.69
    Activations Density 0.043%

    No Known Activations