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

    Neuronpedia

    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. 4-RES-JB
    11. 7060
    Prev
    Next
    INDEX
    Explanations

    words related to quests or inquiries

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "quest" or variations thereof

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

    No Comments

    Negative Logits
    hiba
    -0.80
    女
    -0.77
    inges
    -0.72
    Ĥ¬
    -0.67
     warming
    -0.66
    jriwal
    -0.66
    zzle
    -0.64
     slic
    -0.64
    aphael
    -0.64
     concentration
    -0.63
    POSITIVE LOGITS
    ioned
    1.32
    naire
    1.19
    ions
    1.07
    illes
    0.85
    ion
    0.84
    rane
    0.82
    naires
    0.81
    ION
    0.79
    rade
    0.79
    imation
    0.77
    Activations Density 0.018%

    No Known Activations