© 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. 4-RES-SM
    11. 10079
    Prev
    Next
    INDEX
    Explanations

    instances of financial fraud or deception

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    +0.27
    1.6%
    78
    +0.18
    1.1%
    9
    +0.16
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    9
    +0.27
    0.05
    326
    +0.18
    0.06
    386
    +0.16
    0.01
    Negative Logits
    ĸ´
    -3.04
    ĻĤ
    -2.98
    ½
    -2.94
    ²
    -2.89
    ¬
    -2.87
    º
    -2.81
    Ī
    -2.78
    <|outofrange|>
    -2.76
    -2.76
    ↵            ↵
    -2.76
    POSITIVE LOGITS
    ary
    1.79
    ing
    1.77
    lined
    1.72
    ened
    1.70
     ratio
    1.69
    rich
    1.59
    ting
    1.58
    -
    1.57
    ning
    1.52
    ated
    1.49
    Activations Density 0.813%

    No Known Activations