© 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. 27045
    Prev
    Next
    INDEX
    Explanations

    C++ header file inclusion directives

    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
    478
    +0.12
    0.7%
    47
    +0.12
    0.7%
    72
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    242
    +0.12
    0.03
    222
    +0.12
    0.03
    453
    +0.11
    0.03
    Negative Logits
    à±į
    -2.10
    à±ģ
    -2.03
    ?’
    -1.76
    Ĺ
    -1.74
    à°¿
    -1.66
    thon
    -1.53
    lers
    -1.53
    row
    -1.51
    Ļ
    -1.48
    otoxin
    -1.47
    POSITIVE LOGITS
     constants
    1.57
     empir
    1.46
     constant
    1.43
     Dictionary
    1.34
     arguments
    1.33
     them
    1.30
    /âĪĴ
    1.30
    thems
    1.28
     miles
    1.27
    OURCES
    1.26
    Activations Density 0.069%

    No Known Activations