© 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. 4-RES-JB
    11. 61
    Prev
    Next
    INDEX
    Explanations

    special characters such as "âĢĻ"

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of a specific character or sequence in the text

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

    No Comments

    Negative Logits
     fortun
    -0.85
     adolesc
    -0.81
     mathemat
    -0.80
     Seym
    -0.78
     decimal
    -0.71
     Scrib
    -0.67
     Gutenberg
    -0.67
     deterrent
    -0.67
     spur
    -0.67
     pyramid
    -0.67
    POSITIVE LOGITS
    ï¸ı
    0.97
    ··
    0.93
    strong
    0.89
    sure
    0.88
    own
    0.87
    sa
    0.81
    mate
    0.81
    safe
    0.80
    hole
    0.79
    ski
    0.78
    Activations Density 0.438%

    No Known Activations