Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 11178
    Prev
    Next
    INDEX
    Explanations

    positive adjectives describing events or actions

    oai_token-act-pair · gpt-3.5-turbo

    descriptive adjectives indicating significance or impact

    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
    Ingredients
    -0.94
    onyms
    -0.90
    anguages
    -0.86
     Tanks
    -0.80
    docs
    -0.80
    stocks
    -0.78
    iddles
    -0.77
    classes
    -0.75
    amm
    -0.75
    anders
    -0.73
    POSITIVE LOGITS
     announcement
    1.30
     rebuke
    1.17
     accomplishment
    1.16
     reversal
    1.15
     milestone
    1.14
     victory
    1.14
     achievement
    1.13
     setback
    1.12
     foray
    1.09
     blow
    1.07
    Activations Density 0.178%

    No Known Activations