© 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. 4-RES-JB
    11. 24078
    Prev
    Next
    INDEX
    Explanations

    phrases related to combating various issues such as violence, terrorism, human trafficking, climate change, and misconceptions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "combat" in various contexts related to fighting against negative issues

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

    No Comments

    Negative Logits
    owned
    -0.70
     Zup
    -0.69
    cade
    -0.64
    lov
    -0.61
     Drawn
    -0.60
    Num
    -0.60
    RIP
    -0.60
     sprinkled
    -0.59
    Lib
    -0.59
    Beer
    -0.59
    POSITIVE LOGITS
    tackle
    0.81
     systemic
    0.77
    balance
    0.77
     prevention
    0.74
     counteract
    0.72
    uate
    0.70
     combating
    0.70
     mitigation
    0.70
    ulate
    0.70
     countering
    0.70
    Activations Density 0.216%

    No Known Activations