© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 6496
    Prev
    Next
    INDEX
    Explanations

    references to the term "Diamond."

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Diamond" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mble
    -0.93
    terness
    -0.71
    verend
    -0.70
    Dispatch
    -0.66
    alach
    -0.66
    ĥ
    -0.66
    ORTS
    -0.65
    ãĥĦ
    -0.65
    cha
    -0.65
    ilities
    -0.65
    POSITIVE LOGITS
    iamond
    0.99
    vertisement
    0.87
     Jub
    0.86
    backs
    0.85
     diamond
    0.84
    cart
    0.84
     chloride
    0.84
    mine
    0.84
     mined
    0.81
    hill
    0.80
    Activations Density 0.028%

    No Known Activations