© 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. 24636
    Prev
    Next
    INDEX
    Explanations

    sentences that end with a period

    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
    425
    +0.15
    0.8%
    356
    +0.13
    0.7%
    152
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.15
    0.30
    156
    +0.13
    0.14
    271
    +0.12
    0.14
    Negative Logits
     forth
    -1.69
     agent
    -1.66
    Agent
    -1.54
    enium
    -1.49
    jour
    -1.48
     sacrifices
    -1.45
    agent
    -1.44
     scout
    -1.39
    AZ
    -1.38
    )],
    -1.37
    POSITIVE LOGITS
    ¿½
    3.16
    ©
    2.84
    ij
    2.81
    ¡
    2.79
    ¢
    2.61
    ¨
    2.59
    Ŀ
    2.55
    ľ
    2.49
    «
    2.49
    Ħ
    2.47
    Activations Density 0.235%

    No Known Activations