© 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. 11-RES-JB
    11. 7794
    Prev
    Next
    INDEX
    Explanations

    phrases related to cause and effect

    oai_token-act-pair · gpt-3.5-turbo

    specific recurring phrases or words that suggest rules and consequences in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Historically
    -0.76
    abee
    -0.75
    ibaba
    -0.75
    estone
    -0.74
    inspired
    -0.72
    allel
    -0.71
    Columb
    -0.70
    derived
    -0.69
    cum
    -0.68
    umen
    -0.68
    POSITIVE LOGITS
     consequences
    1.22
     slightest
    1.22
     rest
    1.15
     odds
    1.11
     guy
    1.10
     repercussions
    1.05
     fuck
    1.05
     situation
    1.04
     truth
    1.04
     outcome
    1.02
    Activations Density 0.385%

    No Known Activations