© 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. 4-RES-JB
    11. 10398
    Prev
    Next
    INDEX
    Explanations

    phrases indicating possession

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns indicating personal ownership or experience

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

    No Comments

    Negative Logits
    itect
    -0.93
     Uriel
    -0.72
     Edison
    -0.69
     Izan
    -0.67
     guiIcon
    -0.66
    ciation
    -0.65
    Texture
    -0.65
     apiece
    -0.65
    illary
    -0.64
    DragonMagazine
    -0.64
    POSITIVE LOGITS
     own
    1.33
    anmar
    1.20
    ocard
    1.10
    stery
    1.09
    opia
    1.08
    riad
    1.02
    opic
    1.00
     favorite
    1.00
     favourite
    0.96
     dad
    0.96
    Activations Density 0.122%

    No Known Activations