© 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. 28557
    Prev
    Next
    INDEX
    Explanations

    sentences that convey completion or conclude thoughts

    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
    489
    +0.12
    0.6%
    10
    +0.10
    0.6%
    378
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.12
    0.09
    271
    +0.10
    0.04
    156
    +0.10
    0.04
    Negative Logits
    ¦
    -2.37
    Ħ
    -2.37
    »¿
    -2.32
    »
    -2.28
    ¥
    -2.15
    £
    -2.10
    ½
    -2.06
    §
    -2.06
    ©
    -2.04
    ĸ´
    -2.02
    POSITIVE LOGITS
    onymous
    1.81
     Bundes
    1.56
    éric
    1.44
    ygen
    1.40
    ECD
    1.40
    efs
    1.39
    OID
    1.37
    ogene
    1.35
    OVID
    1.34
    dorff
    1.31
    Activations Density 0.032%

    No Known Activations