© 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. 10171
    Prev
    Next
    INDEX
    Explanations

    technical terms related to engineering and mechanisms

    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
    307
    +0.24
    1.4%
    466
    +0.21
    1.2%
    306
    +0.16
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    47
    +0.24
    0.03
    173
    +0.21
    0.03
    445
    +0.16
    0.03
    Negative Logits
    RESULTS
    -1.60
    Appeal
    -1.56
    ^](#
    -1.55
    ict
    -1.48
    ottenham
    -1.47
    áĢº
    -1.43
    erad
    -1.42
    arias
    -1.41
    =%
    -1.41
    ciparum
    -1.39
    POSITIVE LOGITS
     Patent
    2.30
     plurality
    2.05
     thereon
    2.03
     FIGS
    2.00
     therein
    1.92
     various
    1.87
     apparatus
    1.85
     apparatuses
    1.83
     such
    1.82
    ħ
    1.82
    Activations Density 0.143%

    No Known Activations