© 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. 7-RES-JB
    11. 3610
    Prev
    Next
    INDEX
    Explanations

    mentions of the word 'Buff' with various prefixes and suffixes

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Buff," particularly in various contexts and associations

    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
    FTWARE
    -0.70
     Stras
    -0.67
    ________________________
    -0.67
    PLAY
    -0.64
     Labyrinth
    -0.63
    worldly
    -0.60
     Herrera
    -0.60
     Worlds
    -0.60
    QUIRE
    -0.58
    dfx
    -0.58
    POSITIVE LOGITS
    alos
    1.13
    alon
    1.11
    ered
    1.06
    alo
    1.05
    oon
    1.02
    aign
    0.96
    ering
    0.96
    ett
    0.94
    enstein
    0.93
    oons
    0.91
    Activations Density 0.027%

    No Known Activations