Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 19055
    Prev
    Next
    INDEX
    Explanations

    The neuron is looking for chemical compound names

    oai_token-act-pair · gpt-3.5-turbo

    chemical compounds and their structural components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gunn
    -0.83
     Leone
    -0.74
     Jaw
    -0.70
     Unlimited
    -0.68
     Nights
    -0.68
     Journey
    -0.65
     Revenue
    -0.64
     Gateway
    -0.64
     Wonderland
    -0.63
     Dive
    -0.63
    POSITIVE LOGITS
     acids
    1.37
    acet
    1.11
     acid
    1.10
    chlor
    1.09
    oxy
    1.07
     chloride
    1.06
     phosphate
    1.05
     gluc
    1.05
    acid
    1.05
    hyd
    1.05
    Activations Density 0.071%

    No Known Activations