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. 3-RES-JB
    6. 7634
    Prev
    Next
    INDEX
    Explanations

    the name "Flushing" in the text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Flushing" in relation to various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eers
    -0.87
    terday
    -0.84
    eering
    -0.78
    anwhile
    -0.77
    ettings
    -0.73
    eer
    -0.70
    selves
    -0.69
    ħĭ
    -0.67
     conclud
    -0.67
    EngineDebug
    -0.66
    POSITIVE LOGITS
    uffy
    1.15
    avour
    1.14
    acies
    1.07
    iltration
    1.06
    ights
    1.05
    urry
    0.99
    icker
    0.96
    ashing
    0.96
    oss
    0.96
    uff
    0.95
    Activations Density 0.009%

    No Known Activations