© 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. 1-RES-JB
    11. 3619
    Prev
    Next
    INDEX
    Explanations

    the word "flush" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    situations or contexts involving the term "flush" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ourke
    -0.77
    yers
    -0.67
    ordan
    -0.67
    anwhile
    -0.67
    */(
    -0.67
    ãģķ
    -0.64
    ean
    -0.64
    unes
    -0.61
    ramer
    -0.60
     dstg
    -0.59
    POSITIVE LOGITS
     flush
    1.56
     flushed
    1.11
    flush
    0.83
    ysis
    0.76
     toilets
    0.75
    itus
    0.72
    idious
    0.70
    ishable
    0.68
    terness
    0.68
    abouts
    0.65
    Activations Density 0.005%

    No Known Activations