© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 19733
    Prev
    Next
    INDEX
    Explanations

    references to the cloud storage service "Dropbox"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of cloud storage services, particularly Dropbox

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eering
    -0.98
    iew
    -0.72
    orio
    -0.70
    elin
    -0.68
    apo
    -0.68
    Nazi
    -0.65
     Rapp
    -0.63
     Purpose
    -0.63
    azi
    -0.61
    Past
    -0.61
    POSITIVE LOGITS
    drop
    0.88
    phrine
    0.84
    plets
    0.84
    stairs
    0.83
    drops
    0.82
     downed
    0.76
     Dropbox
    0.75
    pped
    0.72
    ried
    0.72
    Drop
    0.71
    Activations Density 0.021%

    No Known Activations