© 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. 21146
    Prev
    Next
    INDEX
    Explanations

    phrases involving the concept of being part of something

    oai_token-act-pair · gpt-3.5-turbo

    references to "the" as part of a larger context or statement

    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
    eers
    -0.82
    aris
    -0.73
     Akin
    -0.69
    arians
    -0.68
    fy
    -0.68
    ãĥ»
    -0.67
     dressed
    -0.65
    atoon
    -0.62
    oons
    -0.61
    aciously
    -0.60
    POSITIVE LOGITS
     equation
    1.02
     larger
    0.99
     realm
    0.90
     wider
    0.86
     broader
    0.86
     ecosystem
    0.81
     solution
    0.80
     continuum
    0.80
     process
    0.79
     same
    0.78
    Activations Density 0.136%

    No Known Activations