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. 9-RES-JB
    6. 12508
    Prev
    Next
    INDEX
    Explanations

    phrases related to raising awareness on various issues and causes

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to raising awareness about social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amina
    -0.68
    anova
    -0.64
    nard
    -0.64
     Majesty
    -0.62
    hire
    -0.60
    amen
    -0.60
    hair
    -0.58
    xit
    -0.58
    nia
    -0.58
    compan
    -0.57
    POSITIVE LOGITS
     awareness
    1.04
     Awareness
    0.97
    awareness
    0.90
    wcs
    0.80
     campaigns
    0.75
    campaign
    0.75
    raising
    0.72
     amongst
    0.68
    isance
    0.67
    yout
    0.67
    Activations Density 0.059%

    No Known Activations