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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3-RES-JB
    11. 15128
    Prev
    Next
    INDEX
    Explanations

    prepositions or adverbs indicating the location or position of something in relation to others

    oai_token-act-pair · gpt-3.5-turbo

    the word "amongst" and its variations, indicating collective or shared experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vi
    -0.68
    iens
    -0.68
    LY
    -0.64
    ending
    -0.63
    Card
    -0.63
     Mour
    -0.62
    tto
    -0.62
    lique
    -0.61
    uez
    -0.61
    iasis
    -0.61
    POSITIVE LOGITS
    sembly
    0.90
     Whilst
    0.87
    ĨĴ
    0.83
    ĵĺ
    0.81
     whilst
    0.79
    merce
    0.76
    alysed
    0.75
     obser
    0.75
     antioxid
    0.72
    ¶ħ
    0.72
    Activations Density 0.030%

    No Known Activations