© 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. 8-RES-JB
    11. 6124
    Prev
    Next
    INDEX
    Explanations

    references or mentions of breast milk, feeding, or related topics

    oai_token-act-pair · gpt-3.5-turbo

    references to breast milk and related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pmwiki
    -0.85
    ADRA
    -0.84
    umar
    -0.79
    mble
    -0.77
    udos
    -0.72
    ahime
    -0.70
    quickShipAvailable
    -0.66
    govtrack
    -0.66
    âĶģ
    -0.64
    ocument
    -0.63
    POSITIVE LOGITS
    plate
    1.23
    fed
    1.18
    bone
    1.09
     implants
    1.01
     milk
    1.01
    feeding
    0.99
    mil
    0.95
     cancer
    0.92
    plates
    0.92
     nipples
    0.89
    Activations Density 0.022%

    No Known Activations