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. 11659
    Prev
    Next
    INDEX
    Explanations

    phrases related to requirements and specifications in various contexts

    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
    436
    +0.20
    1.2%
    276
    +0.15
    0.9%
    240
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    436
    +0.20
    0.06
    240
    +0.15
    -0.01
    424
    +0.14
    0.02
    Negative Logits
    ŀ
    -2.70
    Īĺ
    -2.51
    »
    -2.45
    »¿
    -2.38
    ¢
    -2.24
    Ĥ
    -2.19
    Ĩ
    -2.16
    ½
    -2.11
    Ĥ¬
    -2.08
    º
    -2.08
    POSITIVE LOGITS
    )>
    1.58
     standpoint
    1.51
     ingredients
    1.51
    yle
    1.49
    )",
    1.49
     syll
    1.48
     antigens
    1.43
     career
    1.42
     deficiencies
    1.36
     pane
    1.36
    Activations Density 1.152%

    No Known Activations