© 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. 2-RES-JB
    11. 19962
    Prev
    Next
    INDEX
    Explanations

    references to bisexuality

    oai_token-act-pair · gpt-3.5-turbo

    references to bisexuality and related discussions about it

    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
    EMS
    -0.77
    urers
    -0.76
    EAR
    -0.73
    LV
    -0.71
    steen
    -0.71
     Amend
    -0.69
    efer
    -0.68
    MER
    -0.68
    VEN
    -0.67
    IVER
    -0.66
    POSITIVE LOGITS
    ity
    1.10
     bisexual
    1.02
    isexual
    0.92
     citiz
    0.82
    etooth
    0.79
    icide
    0.77
    iliary
    0.77
    itarian
    0.76
    antically
    0.76
    esity
    0.74
    Activations Density 0.006%

    No Known Activations