© 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. 7-RES-JB
    11. 2873
    Prev
    Next
    INDEX
    Explanations

    words related to cultivation or cultivating

    oai_token-act-pair · gpt-3.5-turbo

    terms related to cultivation and refinement processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    driver
    -0.77
    stop
    -0.76
    olina
    -0.76
    estone
    -0.73
    swick
    -0.72
    head
    -0.72
    iny
    -0.71
    quartered
    -0.69
    lines
    -0.68
    eworld
    -0.68
    POSITIVE LOGITS
     Seym
    0.67
    xual
    0.66
     bred
    0.66
    aughs
    0.66
    ModLoader
    0.65
     cultivated
    0.65
    naissance
    0.62
    zinski
    0.61
     guiActiveUnfocused
    0.61
    ivating
    0.60
    Activations Density 0.095%

    No Known Activations