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. 3458
    Prev
    Next
    INDEX
    Explanations

    phrases related to airborne diseases or military units

    oai_token-act-pair · gpt-3.5-turbo

    references to airborne and borne diseases or conditions

    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
    ebus
    -0.98
    etsk
    -0.84
    otaur
    -0.79
    xes
    -0.78
    estamp
    -0.77
    eur
    -0.73
    ffield
    -0.73
    oother
    -0.73
    oir
    -0.72
    este
    -0.72
    POSITIVE LOGITS
    nown
    0.84
     pathogens
    0.75
     tradem
    0.74
    borne
    0.72
     airborne
    0.72
    puter
    0.70
    advertising
    0.69
     condol
    0.69
     audible
    0.69
    aviour
    0.66
    Activations Density 0.038%

    No Known Activations