© 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. 31909
    Prev
    Next
    INDEX
    Explanations

    geographical directions and locations

    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
    119
    +0.14
    0.8%
    326
    +0.14
    0.7%
    468
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    119
    +0.14
    0.02
    468
    +0.14
    0.02
    115
    +0.11
    0.02
    Negative Logits
    ĻĤ
    -2.27
    ENTS
    -1.97
     harmless
    -1.92
    ILITY
    -1.89
     Procedures
    -1.77
    ubicin
    -1.65
    ctors
    -1.63
    OLOG
    -1.63
    éĩı
    -1.62
     Agents
    -1.61
    POSITIVE LOGITS
    ward
    2.59
    wards
    2.51
    western
    1.94
     corridor
    1.92
     east
    1.84
     aisle
    1.79
    cott
    1.74
    line
    1.74
    minster
    1.72
    lund
    1.69
    Activations Density 0.100%

    No Known Activations