© 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. 10-RES-JB
    11. 7778
    Prev
    Next
    INDEX
    Explanations

    phrases related to justification or reasoning

    oai_token-act-pair · gpt-3.5-turbo

    phrases that contain the terms "basis" and "grounds" which are often used to indicate reasoning or justification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ascus
    -0.79
    icer
    -0.74
    quer
    -0.71
    Town
    -0.68
    oppable
    -0.66
    ilde
    -0.65
    edo
    -0.65
    agra
    -0.65
     Sparrow
    -0.64
    resent
    -0.64
    POSITIVE LOGITS
     basis
    1.03
     grounds
    1.03
     Grounds
    0.90
     premise
    0.84
    tyard
    0.78
    grounds
    0.77
    fy
    0.74
    ifiers
    0.73
    mination
    0.73
     principle
    0.73
    Activations Density 0.032%

    No Known Activations