© 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. 9-RES-JB
    11. 15673
    Prev
    Next
    INDEX
    Explanations

    prepositions and articles around certain words

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and phrases that indicate location or direction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icter
    -0.78
    quartered
    -0.70
     Entered
    -0.62
    dor
    -0.62
    ratulations
    -0.59
    ievers
    -0.58
    ctors
    -0.57
    enment
    -0.57
    ounter
    -0.56
    ereo
    -0.55
    POSITIVE LOGITS
     ourselves
    1.07
     yourselves
    1.03
     myself
    1.00
     yourself
    0.97
    Ħ¢
    0.73
     anyway
    0.71
     herself
    0.68
     themselves
    0.68
     own
    0.67
     anyways
    0.66
    Activations Density 0.373%

    No Known Activations