© 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. 8-RES-JB
    11. 1965
    Prev
    Next
    INDEX
    Explanations

    prepositions 'In'

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "In" followed by various contexts or descriptions related to episodes or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    76561
    -0.70
     revoked
    -0.61
    :/
    -0.61
    ALSE
    -0.60
    resh
    -0.60
     unemploy
    -0.59
    reon
    -0.58
    ounty
    -0.58
     endors
    -0.58
    ylum
    -0.58
    POSITIVE LOGITS
     addition
    1.35
     spite
    1.28
    juries
    1.27
    jured
    1.25
    flation
    1.25
    herent
    1.20
    expensive
    1.19
     essence
    1.17
     contrast
    1.16
     fact
    1.15
    Activations Density 0.153%

    No Known Activations