© 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. 11-RES-JB
    11. 22207
    Prev
    Next
    INDEX
    Explanations

    phrases starting with special symbols usually used for quotes or citations

    oai_token-act-pair · gpt-3.5-turbo

    instances of a particular symbol or character, suggesting a focus on specific formatting or notation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     IPM
    -0.63
     shroud
    -0.62
     Dresden
    -0.60
     Isle
    -0.60
     Alive
    -0.59
     airs
    -0.58
     transported
    -0.58
     Alexandria
    -0.58
     manager
    -0.57
     MH
    -0.57
    POSITIVE LOGITS
    ª
    1.39
    ¹
    1.32
    ³
    1.27
    ı
    1.26
    ł
    1.25
    ¦
    1.21
    ½
    1.17
    ©
    1.16
    «
    1.16
    ij
    1.15
    Activations Density 0.129%

    No Known Activations