© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 5146
    Prev
    Next
    INDEX
    Explanations

    prepositions and conjunctions connecting people and actions

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "in" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AMY
    -0.72
    mine
    -0.62
     partName
    -0.62
    oult
    -0.62
     archaeologists
    -0.62
    lied
    -0.60
    ochet
    -0.59
    Wr
    -0.59
    plate
    -0.58
    espie
    -0.57
    POSITIVE LOGITS
     whom
    1.03
     IRC
    0.76
     distress
    0.68
     ways
    0.66
     his
    0.63
     hopes
    0.63
     stride
    0.63
     person
    0.63
     dinner
    0.62
     finer
    0.61
    Activations Density 0.264%

    No Known Activations