© 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. 6098
    Prev
    Next
    INDEX
    Explanations

    terms related to important or crucial ideas

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of 'quintessence' and specific names or places

    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
    gro
    -0.71
     miscarriage
    -0.69
    76561
    -0.67
    AAF
    -0.66
    âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦
    -0.66
     partName
    -0.64
    âĢ¦âĢ¦âĢ¦âĢ¦
    -0.62
    PLA
    -0.62
     folding
    -0.61
     palms
    -0.61
    POSITIVE LOGITS
    inal
    1.16
    iem
    1.10
    irement
    1.09
    encies
    1.06
    inet
    1.04
    essential
    1.04
    isition
    1.03
    isitions
    0.98
    inis
    0.96
    ests
    0.95
    Activations Density 0.081%

    No Known Activations