© 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. 3-RES-JB
    11. 670
    Prev
    Next
    INDEX
    Explanations

    phrases related to advising caution

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of caution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WE
    -0.66
    estone
    -0.66
    tein
    -0.65
    assets
    -0.65
    chrom
    -0.64
    Ve
    -0.64
    THING
    -0.64
    ä½ľ
    -0.63
    JECT
    -0.62
    Untitled
    -0.62
    POSITIVE LOGITS
     caution
    1.11
    ary
    0.90
    fully
    0.88
    autions
    0.87
    ously
    0.77
    uci
    0.76
     cautioned
    0.75
     precaution
    0.75
    lessly
    0.73
    antes
    0.71
    Activations Density 0.012%

    No Known Activations