© 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. 10-RES-JB
    11. 20476
    Prev
    Next
    INDEX
    Explanations

    mentions of different sexual orientations, especially bisexuality, and related discussions or misconceptions

    oai_token-act-pair · gpt-3.5-turbo

    references to bisexuality and related sexual identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    frames
    -0.83
    arnaev
    -0.82
    atche
    -0.80
    urers
    -0.76
    alez
    -0.75
    assic
    -0.73
    ammy
    -0.71
    conom
    -0.70
    iago
    -0.69
    Dispatch
    -0.69
    POSITIVE LOGITS
    osexual
    1.10
    ity
    1.07
     bisexual
    0.90
     couples
    0.89
    bian
    0.85
     Spectrum
    0.83
     sexuality
    0.82
     spectrum
    0.80
    bians
    0.79
    isexual
    0.79
    Activations Density 0.036%

    No Known Activations