© 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. 5080
    Prev
    Next
    INDEX
    Explanations

    instances of the word "ensure" followed by an action or condition

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a focus on ensuring compliance or standards

    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
    quickShipAvailable
    -0.88
    BuyableInstoreAndOnline
    -0.83
    æ©
    -0.69
    pmwiki
    -0.69
    EStreamFrame
    -0.67
    laughter
    -0.67
    models
    -0.66
    ¨
    -0.66
     Hancock
    -0.65
    tumblr
    -0.64
    POSITIVE LOGITS
     uninterrupted
    0.80
    ancial
    0.72
     safe
    0.70
     seamless
    0.70
    necessary
    0.67
     adequate
    0.67
     secure
    0.66
     footing
    0.66
    rity
    0.66
    burse
    0.66
    Activations Density 0.191%

    No Known Activations