© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 7073
    Prev
    Next
    INDEX
    Explanations

    The main thing this neuron does is find grammatical terms and language patterns, such as verb forms, plurals, phonological systems, and compound verbs

    oai_token-act-pair · gpt-3.5-turbo

    grammatical terms and concepts in English language structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ONSORED
    -0.86
    GPU
    -0.75
    ileaks
    -0.74
    funding
    -0.74
     Lobby
    -0.73
    Indust
    -0.72
     profitability
    -0.72
     grassroots
    -0.71
    budget
    -0.71
    igun
    -0.70
    POSITIVE LOGITS
     noun
    1.19
     vowel
    1.17
     pronunciation
    1.14
     verbs
    1.14
    tymology
    1.12
     suffix
    1.10
     meanings
    1.04
     pronouns
    1.00
     abbre
    0.99
     notation
    0.99
    Activations Density 0.471%

    No Known Activations