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. 10-RES-JB
    6. 24154
    Prev
    Next
    INDEX
    Explanations

    the uppercase letter 'Q' followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter "Q" followed by a number

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wagen
    -0.90
    fulness
    -0.69
     Proc
    -0.67
     hers
    -0.65
    fitting
    -0.60
     Painter
    -0.59
     Crimson
    -0.59
     ital
    -0.59
    ufact
    -0.59
     Pra
    -0.57
    POSITIVE LOGITS
    UE
    1.31
    ues
    1.22
    WER
    1.18
    ubes
    1.17
    addafi
    1.11
    LD
    1.08
    ued
    1.07
    UI
    1.04
    atari
    1.03
    atar
    1.00
    Activations Density 0.019%

    No Known Activations