© 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. 7-RES-JB
    11. 1778
    Prev
    Next
    INDEX
    Explanations

    philosophical discussions and debates

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to philosophical inquiries and argumentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     neighb
    -0.68
    Cele
    -0.68
    fired
    -0.68
    venge
    -0.65
     Trophy
    -0.63
    interstitial
    -0.62
     festivities
    -0.62
     escorted
    -0.62
    emetery
    -0.60
     commemor
    -0.60
    POSITIVE LOGITS
     empirical
    1.11
     Suppose
    1.05
     philosophers
    1.00
     analogy
    1.00
     methodological
    0.96
     empir
    0.96
     argues
    0.93
     Chomsky
    0.92
     Argument
    0.90
     causation
    0.87
    Activations Density 1.081%

    No Known Activations