© 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. 9-RES-JB
    11. 13528
    Prev
    Next
    INDEX
    Explanations

    phrases and keywords related to the term Q

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific query or question format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wagen
    -0.83
    ufact
    -0.74
    fulness
    -0.71
     hers
    -0.67
    fitting
    -0.64
     Nadu
    -0.63
     Proc
    -0.62
     Awakens
    -0.60
     Colon
    -0.58
     Painter
    -0.58
    POSITIVE LOGITS
    UE
    1.29
    ues
    1.23
    ued
    1.14
    ubes
    1.11
    WER
    1.07
    addafi
    1.06
    atari
    0.99
    LD
    0.95
    atar
    0.94
    wark
    0.92
    Activations Density 0.039%

    No Known Activations