© 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. 12341
    Prev
    Next
    INDEX
    Explanations

    elements related to structured data or organization

    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
    186
    +0.22
    1.3%
    83
    +0.13
    0.8%
    507
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    437
    +0.22
    0.15
    265
    +0.13
    0.12
    9
    +0.13
    0.12
    Negative Logits
    blr
    -1.57
    cdn
    -1.46
     basis
    -1.45
    fun
    -1.39
     tex
    -1.39
     rx
    -1.38
    arf
    -1.37
    .*]{},
    -1.35
     vein
    -1.35
     tx
    -1.32
    POSITIVE LOGITS
    į
    2.73
    ¶
    2.71
    ļ
    2.58
    º
    2.58
    ħ
    2.46
    ·¸
    2.43
    Ł
    2.41
    ĩ
    2.36
    ł
    2.35
    ĭ
    2.34
    Activations Density 4.467%

    No Known Activations