© 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. 13973
    Prev
    Next
    INDEX
    Explanations

    prepositions indicating direction or position

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and relational phrases indicating connections or 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
    break
    -0.64
    craft
    -0.64
    cake
    -0.62
    glass
    -0.59
    alogue
    -0.59
    igr
    -0.58
    ãĥ³ãĤ¸
    -0.58
    Pg
    -0.57
    horn
    -0.56
    art
    -0.55
    POSITIVE LOGITS
     whom
    1.13
     which
    1.02
    which
    0.82
     whence
    0.80
     determining
    0.75
     respectively
    0.75
     ensuring
    0.71
     minimizing
    0.69
     recommending
    0.67
     allowing
    0.67
    Activations Density 0.627%

    No Known Activations