© 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 EvalsExportsinterp-engineNEWAPI 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. 9265
    Prev
    Next
    INDEX
    Explanations

    numeric values and mathematical expressions

    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
    255
    +0.11
    0.6%
    93
    +0.10
    0.6%
    454
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    92
    +0.11
    0.01
    93
    +0.10
    0.01
    255
    +0.10
    0.00
    Negative Logits
    kin
    -1.56
     sidebar
    -1.40
    verted
    -1.34
    .<
    -1.31
     dispers
    -1.31
    enstein
    -1.30
     founded
    -1.29
     decided
    -1.29
    chers
    -1.26
     appropriate
    -1.25
    POSITIVE LOGITS
    IJ
    2.25
    ©
    2.10
    ī
    2.04
    ¦
    1.93
    ľĵ
    1.92
    Īĺ
    1.87
    ĺ
    1.80
    »
    1.79
    ±
    1.78
    ĵ
    1.76
    Activations Density 0.044%

    No Known Activations