© 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. 8960
    Prev
    Next
    INDEX
    Explanations

    terms related to different sexual orientations, focusing especially on the concept of being straight

    oai_token-act-pair · gpt-3.5-turbo

    references to heterosexual identity and related discussions

    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
    è¦ļéĨĴ
    -0.69
     Kard
    -0.66
    adle
    -0.66
     Lauder
    -0.65
    auder
    -0.65
     Tycoon
    -0.64
    mble
    -0.63
     Oro
    -0.63
     ILCS
    -0.62
     Ji
    -0.62
    POSITIVE LOGITS
    bent
    0.95
    ibur
    0.95
    straight
    0.92
    forward
    0.89
    Stra
    0.86
     Straight
    0.86
    bread
    0.78
    FIX
    0.78
    away
    0.77
     dope
    0.77
    Activations Density 0.005%

    No Known Activations