© 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. 2-RES-JB
    11. 24225
    Prev
    Next
    INDEX
    Explanations

    mentions of various types of amines and their effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words related to chemicals and drugs, particularly those ending in 'amine'

    oai_token-act-pair · gpt-3.5-turbo
    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
    Rated
    -0.74
    reek
    -0.72
    Leary
    -0.71
     AES
    -0.69
    deck
    -0.69
    Earth
    -0.67
     IEEE
    -0.67
    MET
    -0.67
     AAP
    -0.66
     MET
    -0.65
    POSITIVE LOGITS
    amine
    1.38
    amines
    1.18
    phrine
    1.06
    ergic
    0.97
    ividual
    0.88
    ption
    0.87
    oline
    0.80
    opol
    0.79
    ivery
    0.77
    gdala
    0.77
    Activations Density 0.017%

    No Known Activations