© 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. 4-RES-SM
    11. 12855
    Prev
    Next
    INDEX
    Explanations

    special characters or symbols

    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
    271
    +0.38
    2.3%
    64
    +0.25
    1.5%
    290
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.38
    0.26
    156
    +0.25
    0.21
    271
    +0.12
    0.09
    Negative Logits
     Hammond
    -1.69
    itud
    -1.56
    illery
    -1.55
     Coul
    -1.55
     Louisiana
    -1.52
     Perry
    -1.49
     Orleans
    -1.48
    sects
    -1.44
     shotgun
    -1.43
     stakes
    -1.41
    POSITIVE LOGITS
    ½
    4.84
    ¨
    4.72
    «
    4.67
    ¯
    4.67
    Į
    4.67
    ħ
    4.66
    į
    4.65
    ¿
    4.64
    Ĵ
    4.64
    ©
    4.63
    Activations Density 1.278%

    No Known Activations