© 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. 11436
    Prev
    Next
    INDEX
    Explanations

    sentences beginning with "As" where the speaker describes their role or identity and shares a personal viewpoint

    oai_token-act-pair · gpt-3.5-turbo

    references to personal identity and roles within a community context

    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
    »Ĵ
    -0.70
    arat
    -0.69
    OTO
    -0.68
     Goods
    -0.63
    Reloaded
    -0.62
    Removed
    -0.62
     vanished
    -0.62
    feat
    -0.62
     Emin
    -0.61
    Score
    -0.58
    POSITIVE LOGITS
     intimately
    0.90
     myself
    0.81
     firsthand
    0.80
     instinctively
    0.77
     surely
    0.76
    idents
    0.74
     acutely
    0.74
     empath
    0.73
     naturally
    0.73
     I
    0.70
    Activations Density 0.178%

    No Known Activations