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. 2-RES-JB
    6. 8547
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions, particularly those related to the skin

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific plant-related terms or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    drawn
    -0.81
    testing
    -0.74
    interrupted
    -0.70
     penetrating
    -0.64
    chlor
    -0.64
     Commodore
    -0.63
    lessness
    -0.63
    Cand
    -0.62
    cussion
    -0.61
    ysis
    -0.61
    POSITIVE LOGITS
    azo
    1.00
    olkien
    0.91
    urnal
    0.88
    arget
    0.88
    olith
    0.87
    oday
    0.86
    yt
    0.85
    rox
    0.83
    te
    0.82
    apest
    0.81
    Activations Density 0.005%

    No Known Activations