© 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. 3-RES-JB
    11. 9097
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a recent event or change

    oai_token-act-pair · gpt-3.5-turbo

    references to time, specifically the word "Since" followed by a time indicator

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jew
    -0.68
    abus
    -0.67
    amina
    -0.66
    ABLE
    -0.64
     lymph
    -0.64
    natureconservancy
    -0.64
    iddler
    -0.63
     lookout
    -0.63
    æ©
    -0.62
    amount
    -0.62
    POSITIVE LOGITS
    rely
    1.29
    ĸļ
    0.91
    pite
    0.81
     1979
    0.75
     1961
    0.72
    gery
    0.72
     1981
    0.69
     1946
    0.69
     1971
    0.68
     2006
    0.68
    Activations Density 0.033%

    No Known Activations