© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 17228
    Prev
    Next
    INDEX
    Explanations

    instances of the word "mother" with high activation values

    oai_token-act-pair · gpt-3.5-turbo

    references to family members, particularly mothers and fathers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    intensity
    -0.72
    uters
    -0.71
    mble
    -0.68
    atility
    -0.68
    arcity
    -0.67
    estyles
    -0.66
    uers
    -0.66
    ensitivity
    -0.63
    ilateral
    -0.63
    uve
    -0.62
    POSITIVE LOGITS
    hood
    0.86
     uncle
    0.85
    ma
    0.79
     grandmother
    0.78
     aunt
    0.76
     ancestor
    0.74
     niece
    0.72
     disappro
    0.72
     mummy
    0.71
    parents
    0.70
    Activations Density 0.076%

    No Known Activations