© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 2761
    Prev
    Next
    INDEX
    Explanations

    the word "ena" or "Ena" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    the name "Elena" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     select
    -0.62
     precisely
    -0.62
     tob
    -0.60
     Rail
    -0.60
     PRESS
    -0.60
     propriet
    -0.59
     rail
    -0.59
     where
    -0.59
     Freed
    -0.58
     tick
    -0.58
    POSITIVE LOGITS
    ena
    4.57
    ENA
    1.91
    eno
    1.66
    enes
    1.48
    enic
    1.34
    ela
    1.33
    eni
    1.33
    ene
    1.31
    eva
    1.23
    enos
    1.22
    Activations Density 0.013%

    No Known Activations