© 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. 9-RES-JB
    11. 8607
    Prev
    Next
    INDEX
    Explanations

    Italian words

    oai_token-act-pair · gpt-3.5-turbo

    terms related to digital information and analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bench
    -0.63
    Moore
    -0.62
    made
    -0.60
    luck
    -0.60
    short
    -0.59
    rified
    -0.57
    USD
    -0.57
    TP
    -0.57
    Tokens
    -0.57
    Sadly
    -0.56
    POSITIVE LOGITS
    ñ
    1.00
    ÃŁ
    0.93
    ë
    0.90
    ennes
    0.90
    endas
    0.89
    ð
    0.89
    Äĩ
    0.88
    endum
    0.87
    Å¡
    0.85
    ño
    0.84
    Activations Density 0.105%

    No Known Activations