© 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. 11-RES-JB
    11. 14869
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "over the"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "over the" and variations thereof

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istry
    -0.75
    nery
    -0.75
    vana
    -0.72
    behind
    -0.70
    nell
    -0.66
    inas
    -0.66
    nas
    -0.66
    isma
    -0.65
    weapons
    -0.64
    days
    -0.64
    POSITIVE LOGITS
     hump
    1.05
     horizon
    0.99
     objections
    0.97
     shoulder
    0.93
     objection
    0.88
     top
    0.87
     railing
    0.87
     edge
    0.86
     rooft
    0.85
     fence
    0.83
    Activations Density 0.059%

    No Known Activations