© 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. 6-RES-JB
    11. 18456
    Prev
    Next
    INDEX
    Explanations

    words related to childbirth and newborns

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "born" in relation to babies or newborns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uyomi
    -0.92
     Flavoring
    -0.82
    awaru
    -0.80
     lawy
    -0.78
    xtap
    -0.78
    intendent
    -0.73
    dden
    -0.73
    ahime
    -0.72
    eredith
    -0.71
    urat
    -0.71
    POSITIVE LOGITS
     babies
    0.88
    lings
    0.84
    days
    0.81
    birth
    0.79
     prematurely
    0.77
    weight
    0.77
     infants
    0.73
     kittens
    0.72
     embryos
    0.67
     canal
    0.67
    Activations Density 0.041%

    No Known Activations