© 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. 2-RES-SM
    11. 12358
    Prev
    Next
    INDEX
    Explanations

    formal language used in descriptions and disclosures, particularly in technical or scientific contexts

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    268
    +0.12
    0.7%
    115
    +0.11
    0.6%
    280
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    236
    +0.12
    0.07
    268
    +0.11
    0.08
    463
    +0.10
    0.05
    Negative Logits
    ĥ½
    -2.93
    ½
    -2.92
    ¼
    -2.67
    »¿
    -2.66
    ĵ
    -2.53
     ↵
    -2.44
    č↵
    -2.44
    ↵
    -2.44
    ↵
    -2.44
    ↵
    -2.44
    POSITIVE LOGITS
     adj
    1.55
    entially
    1.51
     geomet
    1.50
    anto
    1.49
     iter
    1.48
    ibus
    1.47
     among
    1.46
    ring
    1.44
     redund
    1.44
    cke
    1.44
    Activations Density 0.503%

    No Known Activations