© 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. 2-RES-JB
    11. 12699
    Prev
    Next
    INDEX
    Explanations

    pronouns referring to a female subject

    oai_token-act-pair · gpt-3.5-turbo

    references to a central female character or subject

    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
    natureconservancy
    -0.68
     »
    -0.66
     expense
    -0.65
    OTAL
    -0.65
    merce
    -0.64
     avail
    -0.62
     Appearance
    -0.62
     margins
    -0.60
    oday
    -0.60
     wilderness
    -0.60
    POSITIVE LOGITS
    guard
    0.90
    endant
    0.85
    endants
    0.84
    mented
    0.74
    Catal
    0.72
    hire
    0.71
    ovan
    0.71
    ä¸Ĭ
    0.68
    shire
    0.66
    nard
    0.65
    Activations Density 0.000%

    No Known Activations