© 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. 26753
    Prev
    Next
    INDEX
    Explanations

    references to various stations, particularly in a news or broadcasting context

    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
    156
    +0.18
    1.0%
    318
    +0.10
    0.6%
    262
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.18
    0.02
    262
    +0.10
    0.01
    145
    +0.10
    0.02
    Negative Logits
    ĥ½
    -4.20
    ĺ
    -3.91
    ĩ
    -3.75
    Ķ
    -3.72
    ↵
    -3.67
    ↵            ↵
    -3.67
    -3.67
    ↵↵
    -3.67
    -3.67
    -3.67
    POSITIVE LOGITS
    holder
    2.52
    owner
    2.01
    holders
    2.00
     operator
    1.94
     holder
    1.92
     nearest
    1.82
    wide
    1.80
    arity
    1.77
     Station
    1.76
     owner
    1.73
    Activations Density 0.101%

    No Known Activations