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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 22683
    Prev
    Next
    INDEX
    Explanations

    compound verbs

    oai_token-act-pair · gpt-3.5-turbo

    grammatical terms related to parts of speech, particularly verbs and nouns

    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
    MpServer
    -0.82
    utherland
    -0.79
    psey
    -0.78
    jri
    -0.77
    ONSORED
    -0.74
    gian
    -0.72
    cler
    -0.72
     largeDownload
    -0.72
    urga
    -0.71
    hiba
    -0.70
    POSITIVE LOGITS
    verb
    1.05
     verb
    1.01
     verbs
    0.96
     noun
    0.90
     Verb
    0.89
     phrase
    0.82
    ose
    0.82
     phr
    0.82
     phrases
    0.75
     suffix
    0.75
    Activations Density 0.032%

    No Known Activations