© 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. 11-RES-JB
    11. 10230
    Prev
    Next
    INDEX
    Explanations

    phrases related to motherly figures

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "mother" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amaru
    -0.80
    uate
    -0.69
    OUP
    -0.66
    ãĤ¤ãĥĪ
    -0.66
    imaru
    -0.65
    idian
    -0.64
    opoulos
    -0.63
    iannopoulos
    -0.60
    ECT
    -0.60
    NRS
    -0.60
    POSITIVE LOGITS
    hood
    1.25
    ship
    1.24
     Teresa
    1.15
    fuck
    1.12
    ships
    1.07
    boards
    0.98
    maid
    0.94
    daughter
    0.92
    load
    0.92
    hesis
    0.88
    Activations Density 0.054%

    No Known Activations