© 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 EvalsExportsAPI 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. 4835
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by a action verb in the third person

    oai_token-act-pair · gpt-3.5-turbo

    pronouns that refer to individuals or groups

    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
     Anat
    -0.71
     Cliff
    -0.65
     Canaver
    -0.64
    gallery
    -0.63
    math
    -0.63
     Dive
    -0.61
     Denis
    -0.61
     Thoughts
    -0.60
     Matte
    -0.59
     Medline
    -0.59
    POSITIVE LOGITS
    ©¶æ
    0.96
     encount
    0.87
     frequ
    0.85
     contrace
    0.79
     metic
    0.79
     cumbers
    0.79
    arers
    0.78
     deems
    0.76
    've
    0.75
     encountered
    0.75
    Activations Density 0.291%

    No Known Activations