© 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. 25015
    Prev
    Next
    INDEX
    Explanations

    phrases related to consulting and advisory services

    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
    472
    +0.14
    0.8%
    365
    +0.14
    0.8%
    156
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    472
    +0.14
    0.03
    85
    +0.14
    0.02
    365
    +0.13
    0.02
    Negative Logits
    ened
    -1.94
    hoe
    -1.81
    boro
    -1.51
    DOWN
    -1.47
    ports
    -1.45
    pace
    -1.45
    pes
    -1.45
    ansas
    -1.43
    nes
    -1.42
    paces
    -1.41
    POSITIVE LOGITS
    atories
    1.56
    iant
    1.56
    yers
    1.45
    gery
    1.45
    agm
    1.44
     motions
    1.44
    atives
    1.42
    ying
    1.41
    giving
    1.40
     instruments
    1.40
    Activations Density 0.222%

    No Known Activations