© 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. 11-RES-JB
    11. 18699
    Prev
    Next
    INDEX
    Explanations

    the use of personal pronouns like 'I', 'we', 'he', 'they' in text

    oai_token-act-pair · gpt-3.5-turbo

    first-person pronouns and expressions of personal resolve or knowledge

    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
     guiName
    -0.57
     externalToEVAOnly
    -0.56
     Globe
    -0.55
     expire
    -0.53
    hovah
    -0.53
     Explain
    -0.52
     Parables
    -0.51
     summary
    -0.51
     Prepare
    -0.51
    omsky
    -0.50
    POSITIVE LOGITS
     needed
    1.59
     wanted
    1.57
     knew
    1.49
     hadn
    1.49
    'd
    1.44
     cared
    1.39
     liked
    1.36
    needed
    1.34
     hated
    1.32
     wished
    1.32
    Activations Density 0.407%

    No Known Activations