© 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. 2-RES-JB
    11. 9282
    Prev
    Next
    INDEX
    Explanations

    references to the term "minors" in a text, particularly in the context of concerns or actions related to them

    oai_token-act-pair · gpt-3.5-turbo

    references to minors and underage individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¡
    -0.79
    DCS
    -0.72
    ãģĻ
    -0.66
    -+-+-+-+
    -0.66
     Hawks
    -0.66
     charism
    -0.65
    growth
    -0.65
    oise
    -0.63
    glas
    -0.62
    nard
    -0.61
    POSITIVE LOGITS
     minors
    1.10
    uggle
    0.74
     underage
    0.72
     aged
    0.71
    regon
    0.67
     juveniles
    0.67
    uthor
    0.66
     coloring
    0.66
    untled
    0.64
    istry
    0.64
    Activations Density 0.006%

    No Known Activations