© 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. 9-RES-JB
    11. 9879
    Prev
    Next
    INDEX
    Explanations

    phrases related to collaboration and joint efforts

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions that link concepts or items together

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ypes
    -0.82
     Saturdays
    -0.77
    iencies
    -0.76
    cases
    -0.75
    iuses
    -0.75
    ahs
    -0.74
    isks
    -0.73
     Vaugh
    -0.72
    stones
    -0.71
    etsk
    -0.71
    POSITIVE LOGITS
     rider
    0.99
     foe
    0.91
     tenant
    0.91
     spectator
    0.90
     observer
    0.83
     vehicle
    0.82
     follower
    0.81
     guiActiveUnfocused
    0.80
     vendor
    0.80
     employee
    0.80
    Activations Density 0.339%

    No Known Activations