© 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. 9103
    Prev
    Next
    INDEX
    Explanations

    the word "assume" and variations of it

    oai_token-act-pair · gpt-3.5-turbo

    the word "assume" and related variations, indicating the act of taking something for granted or supposing something to be true

    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
    ingen
    -0.75
    HCR
    -0.74
    FTWARE
    -0.74
    psey
    -0.73
    sung
    -0.72
    sterdam
    -0.69
    attle
    -0.68
    asuring
    -0.66
    ixt
    -0.66
    velength
    -0.64
    POSITIVE LOGITS
     responsibility
    0.89
     that
    0.83
     familiarity
    0.81
     ownership
    0.78
     innocence
    0.78
     liability
    0.74
     everyone
    0.74
     ignorance
    0.70
    rely
    0.68
     assumption
    0.68
    Activations Density 0.070%

    No Known Activations