© 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. 20580
    Prev
    Next
    INDEX
    Explanations

    phrases related to making cuts or reductions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to actions of reducing or removing something, particularly in a political or economic 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
    perse
    -0.72
     Moder
    -0.68
     Remastered
    -0.65
    SIGN
    -0.63
    AMY
    -0.61
    Newsletter
    -0.60
    oran
    -0.59
     Refresh
    -0.59
    igma
    -0.58
     Applied
    -0.58
    POSITIVE LOGITS
    thro
    1.24
     corners
    1.15
     ties
    1.11
    scenes
    1.09
    backs
    1.07
     throats
    1.02
     bait
    1.01
    lasses
    1.00
    scene
    1.00
     off
    1.00
    Activations Density 0.037%

    No Known Activations