© 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 EvalsExportsinterp-engineNEWAPI 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. 2749
    Prev
    Next
    INDEX
    Explanations

    the phrase "whole" with various intensities and contexts

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases emphasizing the concept of "whole" in various contexts

    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
    marks
    -0.85
    abilities
    -0.75
    rations
    -0.74
    tips
    -0.71
    chairs
    -0.66
    tops
    -0.65
    ache
    -0.64
    Result
    -0.63
    unes
    -0.63
    Attempts
    -0.61
    POSITIVE LOGITS
    heartedly
    1.43
    hearted
    1.26
     bunch
    1.15
     slew
    1.10
     lot
    1.09
     heap
    0.97
     raft
    0.96
     hog
    0.93
     swath
    0.89
     cloth
    0.82
    Activations Density 0.058%

    No Known Activations