© 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. 11-RES-JB
    11. 5042
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns and related words like "m", "ve", and "ll"

    oai_token-act-pair · gpt-3.5-turbo

    first-person pronouns and expressions of personal intention or action

    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
    pires
    -0.60
     dominance
    -0.57
    uably
    -0.56
    binding
    -0.56
    èĢ
    -0.54
    baby
    -0.54
     adherents
    -0.53
    sym
    -0.53
    itual
    -0.53
     mastery
    -0.52
    POSITIVE LOGITS
     emailed
    1.51
     forwarded
    1.44
     contacted
    1.42
     notified
    1.17
     replied
    1.17
     inquired
    1.16
     alerted
    1.16
     uploaded
    1.07
     checked
    1.06
     texted
    1.05
    Activations Density 0.384%

    No Known Activations