© 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. 4-RES-JB
    11. 15304
    Prev
    Next
    INDEX
    Explanations

    phrases related to showing preference or bias towards something or someone

    oai_token-act-pair · gpt-3.5-turbo

    terms related to favoritism and support

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

    No Comments

    Negative Logits
    prototype
    -0.75
    bridge
    -0.72
    borg
    -0.70
     Creed
    -0.67
    ADVERTISEMENT
    -0.67
    OTT
    -0.67
    ı
    -0.66
    oufl
    -0.65
    gaard
    -0.64
     Gorge
    -0.63
    POSITIVE LOGITS
    itism
    1.74
    ited
    1.02
    ably
    1.00
    itures
    0.85
    hift
    0.83
     favoring
    0.80
    itic
    0.78
    uate
    0.76
    abilia
    0.76
    naire
    0.75
    Activations Density 0.011%

    No Known Activations