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. 1-RES-JB
    6. 23826
    Prev
    Next
    INDEX
    Explanations

    mentions of the chemical element nitrogen

    oai_token-act-pair · gpt-3.5-turbo

    references to nitrogen and its various forms and compounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    psc
    -0.85
    >>>
    -0.85
     CLSID
    -0.83
    ifice
    -0.77
    "]=>
    -0.77
    rers
    -0.75
    dar
    -0.74
    tre
    -0.72
    ealing
    -0.72
    ————————
    -0.71
    POSITIVE LOGITS
     nitrogen
    1.36
     ammonia
    1.25
     fertilizer
    1.24
     oxide
    1.12
     manure
    0.94
     hydrogen
    0.89
     dioxide
    0.86
     phosphorus
    0.86
     emission
    0.86
     chlorine
    0.86
    Activations Density 0.010%

    No Known Activations