© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 14298
    Prev
    Next
    INDEX
    Explanations

    phrases related to dropping off or picking up items or people at specific locations

    oai_token-act-pair · gpt-3.5-turbo

    phrases and contexts related to the action of dropping off

    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
     Latter
    -0.78
    CLA
    -0.72
    ZA
    -0.62
    Administ
    -0.60
    WR
    -0.60
     Welsh
    -0.59
    WM
    -0.59
    )))
    -0.58
     agg
    -0.58
     twisted
    -0.55
    POSITIVE LOGITS
    owship
    0.79
    BuyableInstoreAndOnline
    0.79
    imester
    0.71
    pees
    0.69
    ãģı
    0.69
     Tow
    0.68
    Downloadha
    0.67
    rants
    0.67
    accompan
    0.67
     toilets
    0.65
    Activations Density 0.099%

    No Known Activations