© 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. 12570
    Prev
    Next
    INDEX
    Explanations

    reported speech or quotations from various sources

    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
    307
    +0.28
    1.7%
    306
    +0.19
    1.1%
    69
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.28
    0.11
    306
    +0.19
    0.06
    307
    +0.12
    0.09
    Negative Logits
    dess
    -1.83
    hip
    -1.78
    '?
    -1.66
     alike
    -1.63
    hips
    -1.58
    '))
    -1.57
    itecture
    -1.55
     exists
    -1.45
    iscus
    -1.41
    izontal
    -1.41
    POSITIVE LOGITS
     reporters
    2.53
     Reuters
    2.17
     news
    2.15
     remarks
    2.10
     tweeted
    2.03
     CNN
    2.03
     media
    1.94
     his
    1.91
     comment
    1.88
    ĻĤ
    1.85
    Activations Density 1.040%

    No Known Activations