© 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. 7-RES-JB
    11. 1852
    Prev
    Next
    INDEX
    Explanations

    mentions of the entity "Sky"

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to the "Sky" brand or entity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hesis
    -0.77
    ublic
    -0.74
    ause
    -0.72
    女
    -0.69
     Staples
    -0.68
    ufact
    -0.68
     insensitive
    -0.67
    udes
    -0.67
    aneous
    -0.67
    ests
    -0.66
    POSITIVE LOGITS
    fax
    1.01
    hawks
    0.95
    peak
    0.95
    wing
    0.92
     Trading
    0.90
    hawk
    0.90
    forge
    0.86
    watching
    0.84
    works
    0.83
     Bet
    0.83
    Activations Density 0.016%

    No Known Activations