© 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. 2-RES-SM
    11. 12950
    Prev
    Next
    INDEX
    Explanations

    names of countries or regions

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    9
    +0.14
    0.8%
    234
    +0.13
    0.7%
    141
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    9
    +0.14
    0.09
    147
    +0.13
    0.09
    166
    +0.12
    0.01
    Negative Logits
    ©
    -2.13
    ↵
    -1.96
    ↵
    -1.94
    §
    -1.82
    ↵
    -1.79
    >{
    -1.78
    ]>
    -1.78
    "}](#
    -1.71
    ĻĤ
    -1.67
    ↵
    -1.65
    POSITIVE LOGITS
    redited
    1.44
     etc
    1.41
     Rem
    1.40
     Records
    1.34
     Operation
    1.32
    ographer
    1.29
     Mix
    1.29
     Cum
    1.28
     Counts
    1.28
     Monitoring
    1.27
    Activations Density 2.364%

    No Known Activations