© 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. 6-RES-JB
    11. 1450
    Prev
    Next
    INDEX
    Explanations

    instances of prepositions followed by a specific context of location or time

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "on" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     remake
    -0.74
     someday
    -0.73
     outwe
    -0.67
     honestly
    -0.61
     reim
    -0.59
    umo
    -0.59
     legitimately
    -0.59
     thereof
    -0.59
     unim
    -0.58
     cellul
    -0.57
    POSITIVE LOGITS
    APTER
    0.78
     HuffPost
    0.72
    EVA
    0.70
    foundland
    0.70
    sonian
    0.69
    ortunately
    0.69
     Lines
    0.68
    thodox
    0.67
    imester
    0.67
    np
    0.67
    Activations Density 0.158%

    No Known Activations