© 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. 4-RES-JB
    11. 14943
    Prev
    Next
    INDEX
    Explanations

    phrases related to growing up or maturing

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "grown" in various contexts

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

    No Comments

    Negative Logits
    phis
    -0.90
    uyomi
    -0.74
    arty
    -0.74
    pta
    -0.72
    ioned
    -0.71
    odore
    -0.70
    arted
    -0.70
    isites
    -0.67
     COURT
    -0.65
     prosec
    -0.65
    POSITIVE LOGITS
     grown
    0.74
    escent
    0.71
     adolesc
    0.70
    aroo
    0.69
    agy
    0.69
    oms
    0.67
    OGR
    0.67
    Child
    0.67
    grow
    0.65
     wiser
    0.64
    Activations Density 0.013%

    No Known Activations