© 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. 6-RES-JB
    11. 7887
    Prev
    Next
    INDEX
    Explanations

    references to concepts related to grace and mercy

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "grace" and related themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ALK
    -0.64
    ulhu
    -0.63
    ãĥĥãĥī
    -0.63
    aeda
    -0.60
    ocus
    -0.60
    riber
    -0.59
    algia
    -0.58
    OOL
    -0.58
     Argon
    -0.58
    omething
    -0.58
    POSITIVE LOGITS
    fully
    1.42
    fulness
    1.22
    ful
    1.17
    ibility
    0.96
    FUL
    0.93
    combe
    0.88
    ifully
    0.84
    eous
    0.82
    bread
    0.81
    ously
    0.79
    Activations Density 0.019%

    No Known Activations