© 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. 8-RES-JB
    11. 6240
    Prev
    Next
    INDEX
    Explanations

    personal possessive pronouns coupled with feelings or actions

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns indicating ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wrap
    -0.87
    olkien
    -0.84
    CENT
    -0.77
    isite
    -0.76
    wic
    -0.75
    perse
    -0.74
    ault
    -0.73
    alus
    -0.70
    anish
    -0.70
    inctions
    -0.70
    POSITIVE LOGITS
     doorstep
    1.09
     behalf
    1.00
     throats
    0.97
     dreams
    0.97
     guts
    0.96
     favorite
    0.94
     inbox
    0.91
     psyche
    0.91
     daughter
    0.91
     ears
    0.89
    Activations Density 0.226%

    No Known Activations