© 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. 10-RES-JB
    11. 10728
    Prev
    Next
    INDEX
    Explanations

    mentions of things that are important, notable, or of great significance

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "significant" and variations of its context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ©¶æ
    -1.03
    iverpool
    -0.80
    elf
    -0.76
    eez
    -0.71
    nery
    -0.70
    called
    -0.69
    IDES
    -0.69
    roma
    -0.68
    av
    -0.68
    stein
    -0.67
    POSITIVE LOGITS
     amounts
    1.21
     amount
    1.15
    itarian
    1.13
     portions
    1.05
     differences
    1.02
     quantities
    1.02
     improvement
    0.99
     difference
    0.96
     sums
    0.94
     reductions
    0.94
    Activations Density 0.056%

    No Known Activations