Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 19428
    Prev
    Next
    INDEX
    Explanations

    terms related to the "Deferred Action for Childhood Arrivals" (DACA) program

    oai_token-act-pair · gpt-3.5-turbo

    the term "Deferred Action for Childhood Arrivals" and its related discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.76
     Dragonbound
    -0.76
    sth
    -0.70
    mares
    -0.70
     Sorcerer
    -0.69
     concession
    -0.69
    Reviewer
    -0.66
    akeru
    -0.66
    WHERE
    -0.65
     Mara
    -0.64
    POSITIVE LOGITS
    initions
    1.27
    icit
    1.17
    icient
    1.12
    aults
    1.07
    ences
    1.07
    erred
    1.05
    enses
    1.05
    endant
    1.05
    inite
    1.04
    endants
    1.03
    Activations Density 0.011%

    No Known Activations