© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 19608
    Prev
    Next
    INDEX
    Explanations

    terms related to social issues, especially those concerning gender identity and the practice of solitary confinement

    oai_token-act-pair · gpt-3.5-turbo

    terms related to identities and experiences of marginalized groups, particularly focusing on "cis" identities and the concept of solitary confinement

    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
    ingly
    -0.97
     Tycoon
    -0.81
     Seller
    -0.77
    ageddon
    -0.72
    eering
    -0.72
     Wife
    -0.67
     Races
    -0.67
     seller
    -0.66
    oing
    -0.66
    sung
    -0.65
    POSITIVE LOGITS
     confinement
    0.96
     solitary
    0.85
    medi
    0.76
    ctor
    0.75
     cis
    0.73
    binary
    0.73
    char
    0.71
    tern
    0.70
    cer
    0.70
    cipl
    0.69
    Activations Density 0.018%

    No Known Activations