© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 9828
    Prev
    Next
    INDEX
    Explanations

    sequences and mathematical expressions involving addition and multiplication

    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
    125
    +0.10
    0.6%
    54
    +0.10
    0.6%
    75
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    82
    +0.10
    0.03
    125
    +0.10
    0.03
    445
    +0.10
    0.02
    Negative Logits
    dated
    -1.53
    rapeutic
    -1.52
     magnitudes
    -1.39
    ights
    -1.34
    idently
    -1.33
    onom
    -1.30
    atin
    -1.28
    idential
    -1.28
    eful
    -1.27
     formul
    -1.27
    POSITIVE LOGITS
    ĻĤ
    2.99
    Īĺ
    2.28
    º
    2.23
    Ĺ
    2.20
    Ĥ¬
    2.11
    ¼
    2.04
    ĭ
    2.01
    2.00
    2.00
    <|outofrange|>
    2.00
    Activations Density 0.212%

    No Known Activations