© 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. 9424
    Prev
    Next
    INDEX
    Explanations

    terms related to legal compliance and permissions

    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
    21
    +0.19
    1.2%
    168
    +0.11
    0.7%
    240
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    507
    +0.19
    0.01
    168
    +0.11
    0.01
    501
    +0.11
    0.01
    Negative Logits
     concentrate
    -1.38
    entre
    -1.36
    hers
    -1.36
    irus
    -1.30
    elijk
    -1.29
    gres
    -1.20
    ilate
    -1.19
    elij
    -1.19
    emn
    -1.17
    cheon
    -1.16
    POSITIVE LOGITS
    ³
    3.06
    ©
    2.93
    ģ
    2.89
    ¾
    2.87
    ¹
    2.87
    »
    2.87
    ¿
    2.85
    ŀ
    2.84
    Ī
    2.83
    ²
    2.82
    Activations Density 0.030%

    No Known Activations