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. 2-RES-JB
    6. 22723
    Prev
    Next
    INDEX
    Explanations

    phrases with the word 'da' followed by a numerical value, specifically 'da 9' or 'da 10'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "da"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sburgh
    -1.13
    rition
    -0.90
    ORED
    -0.84
    LESS
    -0.78
    sburg
    -0.76
    ï¸ı
    -0.74
    OTOS
    -0.69
    ship
    -0.68
    ROR
    -0.68
    anwhile
    -0.67
    POSITIVE LOGITS
    isy
    1.07
     da
    1.05
    ft
    0.92
    ques
    0.82
    ivari
    0.78
    qu
    0.76
    uren
    0.75
    atta
    0.75
    que
    0.73
    qus
    0.73
    Activations Density 0.004%

    No Known Activations