© 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. 8-RES-JB
    11. 4284
    Prev
    Next
    INDEX
    Explanations

    propositions or conjunctions that introduce additional information or details in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    the word "which" 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 @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     VIDEOS
    -0.79
    athi
    -0.70
    STE
    -0.69
    MENTS
    -0.67
    Bas
    -0.66
    nor
    -0.65
    Behind
    -0.64
    MENT
    -0.61
    BOX
    -0.61
    WARE
    -0.60
    POSITIVE LOGITS
     consists
    1.10
     translates
    1.09
     comprises
    1.04
     consisted
    0.99
     includes
    0.99
     resulted
    0.97
     incidentally
    0.96
     specializes
    0.96
     originated
    0.94
     encompasses
    0.94
    Activations Density 0.119%

    No Known Activations