© 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 EvalsExportsAPI 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. 30528
    Prev
    Next
    INDEX
    Explanations

    descriptions of visual perspectives and viewpoints

    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
    52
    +0.14
    0.8%
    470
    +0.12
    0.7%
    100
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    52
    +0.14
    0.03
    100
    +0.12
    0.03
    188
    +0.12
    0.01
    Negative Logits
    cember
    -1.86
    iday
    -1.54
    verage
    -1.54
    coma
    -1.53
    vity
    -1.50
    urities
    -1.49
     monot
    -1.44
    ]>
    -1.43
     vitamins
    -1.43
    innati
    -1.40
    POSITIVE LOGITS
    ership
    2.62
    port
    2.17
    points
    1.98
    finder
    1.78
     expressed
    1.75
    ports
    1.75
     framed
    1.71
     Caption
    1.65
    rig
    1.58
    IEW
    1.57
    Activations Density 0.172%

    No Known Activations