© 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. 11-RES-JB
    11. 14938
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a sense of completion or totality

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the concept of "all" or completeness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gee
    -0.67
    bal
    -0.58
    zik
    -0.57
    Enter
    -0.57
    IND
    -0.54
    inth
    -0.54
    WF
    -0.53
    ichen
    -0.53
    IDS
    -0.53
    lander
    -0.53
    POSITIVE LOGITS
     kinds
    1.38
     sorts
    1.34
    igators
    1.21
    igator
    1.01
    ahu
    0.96
    usions
    0.90
     manner
    0.89
    uding
    0.87
    udes
    0.84
     of
    0.83
    Activations Density 0.087%

    No Known Activations