© 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. 23707
    Prev
    Next
    INDEX
    Explanations

    words related to significant shifts or changes in thinking or understanding

    oai_token-act-pair · gpt-3.5-turbo

    various forms and related concepts of the term "paradigm."

    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
    hire
    -0.75
    bleacher
    -0.68
    Downloadha
    -0.66
    adows
    -0.65
    lections
    -0.62
    rated
    -0.61
     Cheong
    -0.60
    glomer
    -0.60
    idan
    -0.60
    Lago
    -0.60
    POSITIVE LOGITS
     paradigm
    1.23
     parad
    1.07
    igmatic
    1.01
     Parad
    0.81
    ĸļ
    0.80
     shift
    0.74
    igm
    0.74
    Ħ¢
    0.73
    atically
    0.71
    ually
    0.69
    Activations Density 0.016%

    No Known Activations