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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 29292
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing exclusivity or singularity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/2-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    419
    +0.17
    1.0%
    500
    +0.15
    0.8%
    78
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    435
    +0.17
    0.05
    500
    +0.15
    0.05
    78
    +0.13
    0.04
    Negative Logits
    ļ
    -1.83
    ĸ
    -1.73
     angles
    -1.64
    Ļ
    -1.59
     generations
    -1.57
     directions
    -1.54
    ¹
    -1.49
     steps
    -1.48
    ories
    -1.48
    rations
    -1.46
    POSITIVE LOGITS
    forge
    1.80
    upon
    1.61
    jam
    1.60
    CTX
    1.59
    yon
    1.58
    xiv
    1.57
     safely
    1.56
    GRP
    1.56
    quote
    1.56
    MTP
    1.55
    Activations Density 0.312%

    No Known Activations