© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 14135
    Prev
    Next
    INDEX
    Explanations

    personal identity and relational references

    oai_token-act-pair · gpt-3.5-turbo

    references to identity and personal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ŃĶ
    -0.76
    ingen
    -0.75
    eties
    -0.73
    cedented
    -0.72
    ģ«
    -0.65
     Atkins
    -0.65
     nowhere
    -0.63
    ²
    -0.63
    İĭ
    -0.63
    vity
    -0.63
    POSITIVE LOGITS
     kidding
    0.97
     rooting
    0.84
     belonged
    0.84
     belongs
    0.80
     belong
    0.79
     idol
    0.77
    abouts
    0.75
     voted
    0.71
     REALLY
    0.71
     target
    0.69
    Activations Density 0.088%

    No Known Activations