© 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. 13831
    Prev
    Next
    INDEX
    Explanations

    information related to transactions, such as order details and deadlines

    oai_token-act-pair · gpt-3.5-turbo

    periods at the end of sentences, indicating the conclusion of statements

    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
    miah
    -0.86
     lately
    -0.84
     amazingly
    -0.77
     mirac
    -0.77
     butcher
    -0.75
     overpower
    -0.74
     savage
    -0.74
     oun
    -0.74
     piled
    -0.73
    azon
    -0.73
    POSITIVE LOGITS
     Otherwise
    1.53
     Alternatively
    1.53
     Additionally
    1.51
     Failure
    1.47
     Please
    1.45
     If
    1.44
     Any
    1.43
     Depending
    1.40
     Unless
    1.39
     Individuals
    1.36
    Activations Density 0.227%

    No Known Activations