© 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. 1-RES-JB
    11. 9362
    Prev
    Next
    INDEX
    Explanations

    references to relationships with a female partner

    oai_token-act-pair · gpt-3.5-turbo

    references to girlfriends in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uchin
    -0.78
     inoc
    -0.77
    omin
    -0.76
    kefeller
    -0.75
    Interstitial
    -0.74
    ocratic
    -0.70
     constitu
    -0.68
     denomin
    -0.67
    anche
    -0.66
    SPONSORED
    -0.66
    POSITIVE LOGITS
     girlfriend
    1.14
    gdala
    1.07
    girlfriend
    1.04
     boyfriend
    0.97
     girlfriends
    0.90
    wife
    0.89
     mistress
    0.76
     Isabel
    0.75
     waitress
    0.75
     Kate
    0.74
    Activations Density 0.008%

    No Known Activations