© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 9926
    Prev
    Next
    INDEX
    Explanations

    the occurrence of the word "LA Galaxy Camps"

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and formatting within text, focusing on sentence structure

    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
     util
    -1.02
     whilst
    -0.86
     Whilst
    -0.84
     Martial
    -0.79
     ageing
    -0.79
     citiz
    -0.77
     endeavour
    -0.76
     manoeuv
    -0.72
     humour
    -0.71
     Firstly
    -0.70
    POSITIVE LOGITS
    Enlarge
    1.03
    Advertisement
    0.99
    —"
    0.95
    PHOTOS
    0.95
     Slate
    0.92
    toggle
    0.92
    NPR
    0.91
    ONSORED
    0.86
    advertisement
    0.85
    Correction
    0.85
    Activations Density 0.587%

    No Known Activations