© 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. 27541
    Prev
    Next
    INDEX
    Explanations

    mentions of significant events and milestones in cinematic history

    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
    +0.20
    1.1%
    387
    +0.15
    0.8%
    354
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    71
    +0.20
    0.11
    156
    +0.15
    0.10
    410
    +0.15
    0.09
    Negative Logits
    ginx
    -1.74
     },
    -1.73
     }}
    -1.71
     */,
    -1.66
     ](
    -1.64
    å®ĥ
    -1.61
    .",
    -1.61
     }
    -1.60
    ëĭĪëĭ¤
    -1.59
    vidia
    -1.57
    POSITIVE LOGITS
    ĵ
    1.81
    Ĵ
    1.77
    ¾
    1.74
    ı
    1.73
    Īĺ
    1.66
    ĭ
    1.65
    Ĩ
    1.64
    Į
    1.63
    ´
    1.63
    ½
    1.60
    Activations Density 1.323%

    No Known Activations