© 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. 12441
    Prev
    Next
    INDEX
    Explanations

    conditions or statements that assess significance or correctness

    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
    198
    +0.17
    1.0%
    102
    +0.16
    0.9%
    9
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2
    +0.17
    0.10
    91
    +0.16
    0.09
    246
    +0.12
    0.10
    Negative Logits
    Īĺ
    -4.09
    ĭ
    -3.92
    ĥ
    -3.90
    ħ
    -3.87
    »¿
    -3.74
    ģ
    -3.69
    Ŀ
    -3.56
    İ
    -3.51
    ľ
    -3.44
    ĻĤ
    -3.39
    POSITIVE LOGITS
    agma
    1.86
     happen
    1.76
     happening
    1.66
     meant
    1.57
    itious
    1.52
     happens
    1.52
     imperative
    1.50
     vagu
    1.43
     mean
    1.43
    agmatic
    1.43
    Activations Density 1.791%

    No Known Activations