Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 18391
    Prev
    Next
    INDEX
    Explanations

    phrases related to the letter "Q"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Q" or associated terms likely referring to the QAnon conspiracy theory

    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
    wagen
    -0.74
     Awakens
    -0.71
    ufact
    -0.71
    fulness
    -0.71
     fullest
    -0.68
     Nadu
    -0.68
    weights
    -0.66
     readable
    -0.65
    éĹĺ
    -0.64
     Lauder
    -0.63
    POSITIVE LOGITS
    UE
    1.13
    ues
    1.04
    ued
    1.02
    addafi
    0.98
    WER
    0.97
    atari
    0.91
    ubes
    0.90
    UI
    0.90
    iu
    0.90
    LD
    0.88
    Activations Density 0.024%

    No Known Activations