© 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. 788
    Prev
    Next
    INDEX
    Explanations

    words related to partnership or engagement, specifically terms like "fiancé" and "fiancée"

    oai_token-act-pair · gpt-4-turbo

    references to relationship statuses and connections between individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to engagements and relationships, particularly involving fiancés

    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
    uyomi
    -0.88
    pmwiki
    -0.81
    izoph
    -0.78
     Cth
    -0.74
    oola
    -0.72
     disg
    -0.71
    overs
    -0.67
     gag
    -0.66
    lain
    -0.65
    interrupted
    -0.64
    POSITIVE LOGITS
    cé
    1.06
    ITAL
    0.85
    è¡
    0.84
    ãĤ¿
    0.84
    itiz
    0.83
    ptive
    0.83
    uary
    0.83
    eur
    0.81
    TION
    0.81
    ces
    0.78
    Activations Density 0.015%

    No Known Activations