© 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. 16147
    Prev
    Next
    INDEX
    Explanations

    pronouns indicating ownership or belonging

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns and related expressions of ownership

    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
    ested
    -0.79
    vier
    -0.76
    hari
    -0.70
    edin
    -0.69
    ved
    -0.64
    endif
    -0.64
    orama
    -0.64
    etheless
    -0.62
    glers
    -0.60
    venants
    -0.59
    POSITIVE LOGITS
     sake
    1.66
     purposes
    1.19
     own
    0.98
     upcoming
    0.93
     birthday
    0.92
     sins
    0.90
     amusement
    0.81
     respective
    0.81
     troubles
    0.80
     sanity
    0.80
    Activations Density 0.076%

    No Known Activations