© 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. 17266
    Prev
    Next
    INDEX
    Explanations

    words related to political figures and events

    oai_token-act-pair · gpt-3.5-turbo

    special characters or non-standard typographical elements

    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
     mathemat
    -0.86
    undai
    -0.81
     horizont
    -0.81
     charism
    -0.80
     myster
    -0.78
    eatures
    -0.78
     simultane
    -0.77
     scrut
    -0.76
     pestic
    -0.75
     incorpor
    -0.74
    POSITIVE LOGITS
    ãĥĥãĥī
    0.96
    âĹ¼
    0.95
    MQ
    0.90
    ï¸ı
    0.88
    deg
    0.86
    é¾į
    0.81
    rd
    0.81
    horn
    0.81
    Īè
    0.79
    UE
    0.76
    Activations Density 0.031%

    No Known Activations