Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 8664
    Prev
    Next
    INDEX
    Explanations

    instances of the word "flush"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "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 @ 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
     Cos
    -0.80
     Missions
    -0.70
     Monteneg
    -0.68
     Attribution
    -0.67
     Javascript
    -0.67
    yth
    -0.66
    Cos
    -0.66
     Materials
    -0.64
    learning
    -0.64
     Mord
    -0.64
    POSITIVE LOGITS
     flush
    4.04
     flushed
    2.26
    flush
    2.15
     blush
    1.29
     inline
    1.19
     refill
    1.06
     purge
    1.01
    ushes
    0.99
     shower
    0.98
     wipe
    0.96
    Activations Density 0.013%

    No Known Activations