© 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. 1885
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases indicating a comparison or relationship between two entities

    oai_token-act-pair · gpt-3.5-turbo

    the word "the" used in various contexts throughout the document

    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
    azel
    -0.82
    nell
    -0.81
    achus
    -0.76
    %%%%
    -0.73
    bye
    -0.72
    Shape
    -0.70
    entimes
    -0.70
    osponsors
    -0.69
    @@
    -0.69
    aii
    -0.67
    POSITIVE LOGITS
     sexes
    1.40
     extremes
    0.99
     genders
    0.91
     ages
    0.89
     combatants
    0.81
     factions
    0.80
     aforementioned
    0.80
     two
    0.78
     disparate
    0.78
     sender
    0.75
    Activations Density 0.110%

    No Known Activations