© 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. 25154
    Prev
    Next
    INDEX
    Explanations

    punctuation marks or symbols that separate elements

    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
    478
    +0.14
    0.8%
    6
    +0.11
    0.7%
    13
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    470
    +0.14
    0.06
    13
    +0.11
    0.05
    157
    +0.11
    0.07
    Negative Logits
    ĻĤ
    -3.10
    ¿½
    -2.70
    ķ
    -2.51
    Ħ
    -2.48
    ģ
    -2.39
    Ł
    -2.29
    ļ
    -2.23
    ¹
    -2.18
    Ĺ
    -2.17
    ¯
    -2.09
    POSITIVE LOGITS
     että
    1.78
    tre
    1.68
     '')
    1.65
     dass
    1.64
     agent
    1.60
    )]{}
    1.58
     subd
    1.47
     ÑĩÑĤо
    1.46
     dire
    1.45
    dern
    1.43
    Activations Density 0.364%

    No Known Activations