© 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. 28904
    Prev
    Next
    INDEX
    Explanations

    instances of reported speech or communication

    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
    443
    +0.15
    0.9%
    185
    +0.15
    0.8%
    23
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    185
    +0.15
    0.05
    443
    +0.15
    0.04
    22
    +0.14
    0.03
    Negative Logits
    hole
    -1.65
    heit
    -1.64
    ]{};
    -1.62
    heid
    -1.49
    isans
    -1.48
    Verlag
    -1.45
    akis
    -1.45
    ivism
    -1.44
    lands
    -1.42
    VEGF
    -1.40
    POSITIVE LOGITS
    ĻĤ
    2.65
    ¦
    2.31
    ↵
    2.22
    ↵↵
    2.22
    2.22
    ↵
    2.22
    č↵
    2.22
    ↵↵↵
    2.22
    ↵
    2.22
    č↵
    2.22
    Activations Density 0.110%

    No Known Activations