© 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. 6-RES-JB
    11. 19718
    Prev
    Next
    INDEX
    Explanations

    terms related to the LGBT community

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the LGBT community

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     guiActiveUnfocused
    -0.78
    anke
    -0.75
    tenance
    -0.70
    frames
    -0.69
     Manufacturer
    -0.68
    urers
    -0.68
    manship
    -0.67
    lain
    -0.66
    oxide
    -0.66
     Hitchcock
    -0.65
    POSITIVE LOGITS
    IQ
    1.05
     equality
    0.87
     rights
    0.83
     activists
    0.82
    atri
    0.75
     Spectrum
    0.75
     transsexual
    0.74
     advocates
    0.74
     representation
    0.74
    LGBT
    0.73
    Activations Density 0.028%

    No Known Activations