© 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. 5878
    Prev
    Next
    INDEX
    Explanations

    extremely specific character sequences

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the symbol 'âĢ'

    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
     Palest
    -0.77
    enegger
    -0.72
     VIDEOS
    -0.66
     segreg
    -0.65
    ESSION
    -0.65
     Zup
    -0.64
     comprom
    -0.64
    lishes
    -0.63
     Palestin
    -0.62
    ifications
    -0.61
    POSITIVE LOGITS
    âĢķ
    1.16
    ¡
    1.01
    £
    0.99
    ª
    0.96
    ¹
    0.95
    Ń
    0.95
    º
    0.94
    ¤
    0.92
    Ĵ
    0.91
    Ķ
    0.91
    Activations Density 0.365%

    No Known Activations