© 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. 1-RES-SM
    11. 24276
    Prev
    Next
    INDEX
    Explanations

    terms related to household and family structures

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    156
    +0.31
    1.8%
    56
    +0.19
    1.1%
    472
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.31
    0.07
    56
    +0.19
    -0.00
    71
    +0.11
    0.06
    Negative Logits
    rency
    -1.54
    eline
    -1.47
    ère
    -1.45
    ways
    -1.42
     Forces
    -1.42
    emy
    -1.41
    enne
    -1.32
    force
    -1.32
    urate
    -1.30
    pace
    -1.30
    POSITIVE LOGITS
    "}](#
    1.67
     sure
    1.39
    mounted
    1.33
     HV
    1.33
    apache
    1.29
     setup
    1.26
    rior
    1.24
    ACH
    1.23
    oster
    1.22
     calc
    1.20
    Activations Density 0.631%

    No Known Activations