© 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. 4-RES-SM
    11. 11163
    Prev
    Next
    INDEX
    Explanations

    the infinitive form of verbs

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    434
    +0.14
    0.8%
    478
    +0.13
    0.7%
    69
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    434
    +0.14
    0.10
    69
    +0.13
    0.11
    393
    +0.13
    0.04
    Negative Logits
    hole
    -1.82
    msgstr
    -1.74
     thereto
    -1.70
     to
    -1.68
    antry
    -1.66
     based
    -1.65
    };
    -1.64
     pursuant
    -1.53
    osta
    -1.51
    Career
    -1.50
    POSITIVE LOGITS
    pless
    2.67
    pping
    2.50
    ppen
    2.48
    wered
    2.47
    ilers
    2.34
     behold
    2.31
    ppers
    2.27
    fu
    2.25
    wing
    2.19
    ppings
    2.08
    Activations Density 0.773%

    No Known Activations