© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 12655
    Prev
    Next
    INDEX
    Explanations

    words related to assumptions or presumptions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "assumption"

    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
    eng
    -0.66
    apers
    -0.63
    uba
    -0.63
    ú
    -0.62
    apes
    -0.59
    ez
    -0.58
     revital
    -0.57
    ®
    -0.57
     commemor
    -0.56
    een
    -0.56
    POSITIVE LOGITS
     assumption
    3.83
     assumptions
    2.40
     presumption
    2.09
     expectation
    1.88
     premise
    1.87
     assum
    1.70
     assumed
    1.66
     implication
    1.65
     misconception
    1.64
     hypothesis
    1.62
    Activations Density 0.016%

    No Known Activations