© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 7305
    Prev
    Next
    INDEX
    Explanations

    mentions of being caring or nurturing

    oai_token-act-pair · gpt-3.5-turbo

    references to notable individuals and themes of care or nurturing

    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
     guiActiveUn
    -0.73
    querade
    -0.72
     stren
    -0.71
    uation
    -0.70
     gag
    -0.70
    undown
    -0.69
    raft
    -0.69
     whipping
    -0.69
    avorite
    -0.68
     betting
    -0.67
    POSITIVE LOGITS
    lett
    0.83
    ¶
    0.83
    lda
    0.81
     Galile
    0.80
    ndra
    0.78
    neau
    0.78
    poons
    0.77
    ij
    0.77
    esome
    0.76
    onica
    0.76
    Activations Density 0.035%

    No Known Activations