© 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. 7823
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by nouns or pronouns

    oai_token-act-pair · gpt-3.5-turbo

    phrases that frequently include the word "in" and its associated contexts

    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
    VERTISEMENT
    -0.70
    omer
    -0.69
    ascript
    -0.66
    urat
    -0.66
    ano
    -0.65
    ophobic
    -0.63
    onom
    -0.60
    onso
    -0.59
     depended
    -0.59
    ãĥ¼ãĥ³
    -0.59
    POSITIVE LOGITS
     here
    1.03
    effic
    0.99
    between
    0.94
     there
    0.89
     nowhere
    0.85
     these
    0.84
    clusions
    0.84
     sight
    0.83
     abundance
    0.81
     regards
    0.81
    Activations Density 0.179%

    No Known Activations