© 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. 16048
    Prev
    Next
    INDEX
    Explanations

    prepositions indicating reason or motivation

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "for" used in various contexts, particularly as a preposition signaling purpose 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
    LAB
    -0.73
    ãĤ©
    -0.70
    é¾
    -0.68
    å°Ĩ
    -0.66
    PAC
    -0.64
    LY
    -0.64
    Contact
    -0.64
    halla
    -0.64
    %]
    -0.64
    urred
    -0.59
    POSITIVE LOGITS
     example
    1.55
     instance
    1.46
    give
    1.44
    bidden
    1.39
    getting
    1.25
    gotten
    1.23
     starters
    1.20
    cing
    1.19
    bid
    1.14
    cible
    1.12
    Activations Density 0.059%

    No Known Activations