© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2-RES-SM
    11. 10848
    Prev
    Next
    INDEX
    Explanations

    file paths and directory structures

    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
    478
    +0.19
    1.0%
    377
    +0.12
    0.7%
    338
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    29
    +0.19
    0.02
    511
    +0.12
    0.02
    338
    +0.11
    0.02
    Negative Logits
    herty
    -1.68
    oding
    -1.60
    ually
    -1.58
    ier
    -1.53
    ogenes
    -1.52
    esis
    -1.52
    ieri
    -1.51
    uries
    -1.50
    atching
    -1.49
    osit
    -1.49
    POSITIVE LOGITS
    Ĭ
    2.40
    Ķ
    2.29
    ¿½
    2.27
    ½
    2.20
    Ŀ
    2.15
    Ħ
    2.12
    ³
    2.08
    ĥ½
    2.07
    ı
    2.04
    ¼
    2.02
    Activations Density 0.094%

    No Known Activations