© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 1-RES-SM
    6. 25463
    Prev
    Next
    INDEX
    Explanations

    instances of the word "return" or its various forms, indicating a focus on the concept of returning or coming back

    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
    221
    +0.13
    0.7%
    64
    +0.12
    0.7%
    351
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    64
    +0.13
    0.04
    511
    +0.12
    0.03
    351
    +0.12
    0.03
    Negative Logits
    »¿
    -3.21
    §
    -3.19
    ĨĴ
    -3.10
    ĥ½
    -3.01
    «
    -2.91
    ĵ
    -2.86
    ©
    -2.81
    ¿
    -2.77
    ĩ
    -2.74
    <|outofrange|>
    -2.72
    POSITIVE LOGITS
     starters
    1.58
    ESULT
    1.52
    ries
    1.46
     vict
    1.44
    ulous
    1.40
     minister
    1.40
     touchdowns
    1.39
    pective
    1.38
    erior
    1.35
    door
    1.35
    Activations Density 0.091%

    No Known Activations