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. 4-RES-JB
    6. 21492
    Prev
    Next
    INDEX
    Explanations

    instances of the word "discharge" in sentences

    oai_token-act-pair · gpt-3.5-turbo

    terms related to discharge and legal consequences

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

    No Comments

    Negative Logits
    aque
    -0.90
    apa
    -0.76
    aques
    -0.74
    */(
    -0.73
    ellen
    -0.71
    ppa
    -0.69
    amar
    -0.69
    Ear
    -0.68
    Cru
    -0.68
     Beir
    -0.67
    POSITIVE LOGITS
     discharge
    1.11
    ysis
    0.92
     discharged
    0.89
    owship
    0.87
    uations
    0.84
    luent
    0.83
    inois
    0.80
    ertation
    0.79
    backs
    0.76
    enture
    0.72
    Activations Density 0.010%

    No Known Activations