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. 4-RES-JB
    6. 22814
    Prev
    Next
    INDEX
    Explanations

    the letter 'G' followed by a single digit

    oai_token-act-pair · gpt-3.5-turbo

    the letter "G" in various contexts

    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
    ĸļ
    -0.78
    terday
    -0.76
    oÄŁ
    -0.68
     vou
    -0.63
     Conquest
    -0.62
    stic
    -0.62
    puter
    -0.60
     retrospect
    -0.60
     htt
    -0.59
     Ruins
    -0.59
    POSITIVE LOGITS
    asp
    1.14
    ossip
    1.09
    irlfriend
    1.09
    oliath
    1.09
    CHQ
    1.05
    reet
    1.04
    reetings
    1.04
    ather
    1.04
    iant
    1.03
    eeks
    1.03
    Activations Density 0.047%

    No Known Activations