© 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. 3-RES-JB
    11. 10756
    Prev
    Next
    INDEX
    Explanations

    terms related to dietary needs and conditions

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

    dietary-related terms and specific dietary requirements

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ships
    -0.82
    ysc
    -0.80
    assy
    -0.80
    alach
    -0.79
     Bees
    -0.79
    ovie
    -0.79
    onies
    -0.77
    oons
    -0.76
    obo
    -0.76
    ufact
    -0.75
    POSITIVE LOGITS
    å£
    0.84
     radiation
    0.79
     variance
    0.75
    soever
    0.72
     antioxidants
    0.71
     antibiotics
    0.70
     protein
    0.70
     allerg
    0.69
     citation
    0.68
     supplements
    0.67
    Activations Density 0.028%

    No Known Activations