© 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. 3-RES-JB
    11. 599
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "mother."

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "mother."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Flavoring
    -0.90
    raviolet
    -0.79
    EY
    -0.77
    ickr
    -0.75
    okers
    -0.74
    jriwal
    -0.71
    NRS
    -0.69
    urat
    -0.68
    EStreamFrame
    -0.67
    idian
    -0.66
    POSITIVE LOGITS
    hood
    1.19
    hesis
    1.08
    heses
    1.00
    ship
    0.96
    mother
    0.95
    hetical
    0.87
    hetically
    0.87
    wife
    0.84
    load
    0.84
    ships
    0.82
    Activations Density 0.022%

    No Known Activations