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

    Neuronpedia

    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. 10-RES-JB
    11. 10347
    Prev
    Next
    INDEX
    Explanations

    personal pronouns followed by verbs

    oai_token-act-pair · gpt-3.5-turbo

    expressions of opinion or belief involving personal sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Delivery
    -0.77
     Proced
    -0.76
    itary
    -0.71
    Results
    -0.70
    Materials
    -0.69
    visible
    -0.68
     sequential
    -0.67
     Appendix
    -0.67
     Landing
    -0.67
    iti
    -0.66
    POSITIVE LOGITS
     despise
    1.92
     dislike
    1.85
     adore
    1.68
     admire
    1.62
     disapprove
    1.58
     hate
    1.57
     hates
    1.51
     sympath
    1.46
     abhor
    1.45
    hate
    1.44
    Activations Density 0.582%

    No Known Activations