© 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. 11-RES-JB
    11. 945
    Prev
    Next
    INDEX
    Explanations

    phrases related to continuous change or growth

    oai_token-act-pair · gpt-3.5-turbo

    the word "ever" in combination with various negative contexts

    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
     Obj
    -0.68
    ription
    -0.68
    hemy
    -0.64
    ournals
    -0.64
    ¶ħ
    -0.60
     Polo
    -0.59
    OULD
    -0.58
     Solitaire
    -0.57
     monop
    -0.57
     TDs
    -0.57
    POSITIVE LOGITS
    green
    1.38
    lasting
    1.16
    changing
    1.09
    growing
    1.06
     evolving
    1.01
    present
    1.00
    increasing
    1.00
    wid
    0.96
    more
    0.95
    loving
    0.94
    Activations Density 0.022%

    No Known Activations