© 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. 4-RES-JB
    11. 22016
    Prev
    Next
    INDEX
    Explanations

    mentions of diamonds

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "diamond."

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

    No Comments

    Negative Logits
    mble
    -0.77
    soType
    -0.70
    alach
    -0.69
     Liberties
    -0.68
    HAHAHAHA
    -0.68
    Dispatch
    -0.67
    ntil
    -0.67
    terness
    -0.66
    ĥ
    -0.66
    mental
    -0.65
    POSITIVE LOGITS
     diamonds
    1.01
     diamond
    0.97
    iamond
    0.94
     mining
    0.83
    mining
    0.81
    cart
    0.81
    mine
    0.81
     mined
    0.80
     chloride
    0.80
    fish
    0.78
    Activations Density 0.009%

    No Known Activations