© 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. 0-RES-JB
    11. 16539
    Prev
    Next
    INDEX
    Explanations

    mentions of intake, particularly related to various contexts such as nutrition, water supply, and induction

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Symb
    -0.72
    Revolution
    -0.64
     Barth
    -0.64
    pects
    -0.64
    Legend
    -0.63
    rob
    -0.62
    pter
    -0.61
     Flags
    -0.60
    pb
    -0.60
    âĺ
    -0.59
    POSITIVE LOGITS
     intake
    3.67
     Intake
    3.13
     intakes
    3.00
     ingestion
    1.55
     consumption
    1.52
     absorption
    1.20
     supplementation
    1.20
     Consumption
    1.17
     carbs
    1.11
     exhaust
    1.10
    Activations Density 0.017%

    No Known Activations