© 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. 17622
    Prev
    Next
    INDEX
    Explanations

    percentages and numerical values

    oai_token-act-pair · gpt-3.5-turbo

    punctuated statements or sentences in the text

    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
     discreet
    -0.89
     boarded
    -0.85
     abduct
    -0.82
     ambush
    -0.82
     organise
    -0.80
     barric
    -0.79
     agent
    -0.78
     calming
    -0.77
     dere
    -0.76
     befriend
    -0.76
    POSITIVE LOGITS
     Additionally
    1.38
     Conversely
    1.35
     Moreover
    1.34
     Overall
    1.32
     Furthermore
    1.30
     Similarly
    1.29
     Likewise
    1.26
     Meanwhile
    1.25
     Compare
    1.25
     Compared
    1.24
    Activations Density 0.417%

    No Known Activations