© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 28621
    Prev
    Next
    INDEX
    Explanations

    technical terms and equations related to physics and mathematics

    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
    +0.14
    0.8%
    448
    +0.11
    0.6%
    12
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    17
    +0.14
    0.00
    320
    +0.11
    0.03
    136
    +0.11
    -0.01
    Negative Logits
    apple
    -1.75
     nothing
    -1.52
    "></
    -1.49
     want
    -1.46
     documentation
    -1.46
     pops
    -1.45
    )...
    -1.44
    ...)
    -1.41
    asek
    -1.40
     Answer
    -1.40
    POSITIVE LOGITS
    »
    2.56
    ¾
    2.52
    Īĺ
    2.52
    Ĩ
    2.41
    ¦
    2.37
    ®
    2.37
    ĨĴ
    2.36
    Ŀ
    2.32
    °
    2.30
    «
    2.21
    Activations Density 0.304%

    No Known Activations