© 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. 14459
    Prev
    Next
    INDEX
    Explanations

    technical specifications of computer hardware components

    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
    348
    +0.18
    1.0%
    466
    +0.17
    0.9%
    25
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    189
    +0.18
    0.08
    162
    +0.17
    0.03
    211
    +0.14
    0.07
    Negative Logits
    Ĭ
    -4.03
    ĥ½
    -3.77
    ij
    -3.75
    ¯
    -3.73
    ³
    -3.70
    ¸
    -3.69
    ī
    -3.68
    ĥ
    -3.67
    Į
    -3.65
    Ĥ¬
    -3.56
    POSITIVE LOGITS
    edia
    2.03
    Fs
    2.00
    OD
    1.88
    s
    1.88
    SEC
    1.86
    ERS
    1.84
    OSS
    1.83
    ERTY
    1.82
    ATA
    1.81
    ESSION
    1.81
    Activations Density 0.741%

    No Known Activations