© 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. 10-RES-JB
    11. 6504
    Prev
    Next
    INDEX
    Explanations

    words associated with supervision or protection, such as 'guardian', 'custody', 'steward', and their variations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to guardianship and custody

    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
    ©¶æ
    -0.75
     Kamp
    -0.68
    çīĪ
    -0.67
     Playoffs
    -0.66
     Countdown
    -0.66
    RESULTS
    -0.65
    omsky
    -0.64
    berman
    -0.63
     Speedway
    -0.62
    senal
    -0.62
    POSITIVE LOGITS
    hip
    1.43
    esses
    1.13
    ial
    1.08
    ess
    1.06
     angel
    1.01
     angels
    0.95
     servants
    0.88
     servant
    0.87
    maid
    0.86
    hips
    0.85
    Activations Density 0.130%

    No Known Activations