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. 22662
    Prev
    Next
    INDEX
    Explanations

    phrases related to the ingestion or administration of substances

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the act of consuming substances, particularly drugs and supplements

    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
     Architects
    -0.84
    Square
    -0.78
    square
    -0.70
    Neigh
    -0.68
     Neigh
    -0.68
     Prosper
    -0.68
     Franco
    -0.68
     Pis
    -0.68
    unity
    -0.65
     Frey
    -0.65
    POSITIVE LOGITS
     ingested
    1.29
     dosage
    1.21
     ingestion
    1.21
     orally
    1.13
    hetamine
    1.12
     doses
    1.04
     medication
    1.02
     ingest
    1.02
     intraven
    1.02
     dose
    1.01
    Activations Density 0.072%

    No Known Activations