© 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. 1-RES-JB
    11. 8734
    Prev
    Next
    INDEX
    Explanations

    phrases related to the mineral "sodium."

    oai_token-act-pair · gpt-3.5-turbo

    references to sodium content in food or substances

    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
     CLSID
    -0.87
    Aust
    -0.76
    fare
    -0.76
    orig
    -0.76
    WER
    -0.75
    OW
    -0.75
    arette
    -0.74
    ovie
    -0.72
     Riders
    -0.72
    ger
    -0.71
    POSITIVE LOGITS
     chloride
    1.47
     potassium
    1.36
     sodium
    1.35
     iod
    1.33
     sulph
    1.27
     fluoride
    1.24
     sulf
    1.20
    assium
    1.18
     nit
    1.11
     glutamate
    1.10
    Activations Density 0.012%

    No Known Activations