© 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. 10541
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to taxation and financial regulations

    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
    +0.25
    1.5%
    235
    +0.17
    1.0%
    326
    +0.17
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    419
    +0.25
    0.08
    216
    +0.17
    0.12
    235
    +0.17
    0.09
    Negative Logits
    Īĺ
    -5.30
    ĥ
    -5.08
    ĸ´
    -5.08
    ↵
    -5.02
    č↵
    -5.02
    -5.02
    -5.02
    ↵
    -5.02
    č↵č↵
    -5.02
            ↵
    -5.02
    POSITIVE LOGITS
    acs
    1.51
    */
    1.43
    \],
    1.37
     across
    1.37
    \].
    1.36
    ↵
    1.35
    \]\].
    1.28
     */
    1.27
    ferencing
    1.27
    âĢ¢
    1.27
    Activations Density 3.313%

    No Known Activations