© 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. 10-RES-JB
    11. 9268
    Prev
    Next
    INDEX
    Explanations

    instances of the word "reduced" or its variations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to reduction or decreasing amounts

    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
    ORE
    -0.64
    andise
    -0.62
    ipe
    -0.61
    words
    -0.60
    ervative
    -0.59
    NING
    -0.59
    ands
    -0.59
    enegger
    -0.59
    aint
    -0.59
    mares
    -0.59
    POSITIVE LOGITS
     visibility
    0.80
     inhib
    0.80
     sidx
    0.79
    ahime
    0.78
     effectiveness
    0.75
    istically
    0.75
    xual
    0.73
     reliance
    0.73
     drastically
    0.72
    icides
    0.69
    Activations Density 0.081%

    No Known Activations