© 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. 28989
    Prev
    Next
    INDEX
    Explanations

    structured data representation elements

    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
    296
    +0.15
    0.9%
    269
    +0.13
    0.7%
    350
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    157
    +0.15
    0.06
    17
    +0.13
    0.01
    136
    +0.12
    -0.02
    Negative Logits
    instein
    -2.16
    selves
    -1.90
    ·¸
    -1.79
    ¿½
    -1.76
    Īĺ
    -1.76
    ¼
    -1.75
    ĺ
    -1.73
    »¿
    -1.69
    ĸ
    -1.67
    roads
    -1.67
    POSITIVE LOGITS
     alarm
    1.66
    ubicin
    1.50
     stride
    1.45
    =”
    1.41
     Convert
    1.40
    catalina
    1.39
     Report
    1.39
    ividual
    1.38
    ="@+
    1.36
     =>
    1.35
    Activations Density 0.760%

    No Known Activations