© 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. 10375
    Prev
    Next
    INDEX
    Explanations

    abbreviations or titles related to professional credentials

    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
    415
    +0.13
    0.7%
    427
    +0.12
    0.7%
    366
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    415
    +0.13
    0.04
    175
    +0.12
    0.03
    427
    +0.10
    0.04
    Negative Logits
    ;}
    -1.69
    disambiguation
    -1.69
    ,}
    -1.59
    })}
    -1.57
     <-
    -1.49
     ):
    -1.48
     \-
    -1.47
     unsuccessful
    -1.46
    oretic
    -1.45
     feature
    -1.44
    POSITIVE LOGITS
    ģ
    2.00
    Ļ
    1.98
    »¿
    1.81
    ª
    1.80
    ³
    1.70
    ĸ
    1.70
    ķ
    1.64
    ±
    1.61
    ľ
    1.59
    ¹
    1.59
    Activations Density 0.137%

    No Known Activations