© 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. 30735
    Prev
    Next
    INDEX
    Explanations

    notable names and terms associated with finance and investment

    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
    +0.17
    1.0%
    258
    +0.15
    0.8%
    225
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    446
    +0.17
    0.02
    503
    +0.15
    0.04
    399
    +0.13
    0.02
    Negative Logits
    iento
    -1.59
    ág
    -1.57
    atur
    -1.55
    ego
    -1.49
    ificantly
    -1.48
    omi
    -1.44
     filled
    -1.42
     apologize
    -1.40
    ushed
    -1.40
    enny
    -1.39
    POSITIVE LOGITS
    ¦
    2.12
    ¸
    1.82
    ļ
    1.80
    ł
    1.78
    ¿
    1.78
    ĻĤ
    1.68
    º
    1.63
    ķ
    1.63
    Ĵ
    1.60
    £
    1.60
    Activations Density 0.498%

    No Known Activations