© 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. 0-RES-JB
    11. 10119
    Prev
    Next
    INDEX
    Explanations

    words related to cause and effect, specifically actions resulting in specific outcomes

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "resulting" and related phrases that indicate causal relationships or consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pheus
    -0.65
    oths
    -0.64
    agall
    -0.59
    berman
    -0.59
    Pac
    -0.58
    î
    -0.57
     dynasty
    -0.56
    iac
    -0.55
     understands
    -0.55
     remind
    -0.55
    POSITIVE LOGITS
     resulting
    3.64
     resultant
    2.78
     ensuing
    2.23
     consequ
    1.93
     result
    1.74
    result
    1.68
     culminating
    1.53
     resulted
    1.47
     accompanying
    1.45
     subsequent
    1.41
    Activations Density 0.009%

    No Known Activations