© 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. 1-RES-SM
    11. 25913
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal disclaimers and conditions of use

    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
    +0.18
    1.0%
    111
    +0.12
    0.7%
    71
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    75
    +0.18
    0.02
    145
    +0.12
    0.02
    468
    +0.10
    0.01
    Negative Logits
    'd
    -1.61
     himself
    -1.46
    ?)
    -1.45
    eth
    -1.40
    ):
    -1.40
    ?).
    -1.34
     wonder
    -1.34
    th
    -1.34
    onic
    -1.33
     hadn
    -1.27
    POSITIVE LOGITS
    ĻĤ
    1.61
     WARRANTIES
    1.38
     prá
    1.31
    inib
    1.31
     soc
    1.30
     propos
    1.29
    们
    1.27
     pend
    1.26
     dalla
    1.25
    ίναι
    1.25
    Activations Density 0.090%

    No Known Activations