© 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. 4-RES-SM
    11. 12208
    Prev
    Next
    INDEX
    Explanations

    negative sentiments or criticisms

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    21
    +0.23
    1.3%
    306
    +0.16
    0.9%
    203
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.23
    0.05
    203
    +0.16
    0.04
    316
    +0.15
    0.04
    Negative Logits
     LICENSE
    -1.49
     hij
    -1.44
     Rings
    -1.44
    hers
    -1.43
     bins
    -1.37
     Cauc
    -1.36
     VII
    -1.36
    orect
    -1.35
     lig
    -1.33
    rendum
    -1.32
    POSITIVE LOGITS
    £
    3.30
    ¾
    3.28
    Ŀ
    3.04
    Ĥ¬
    2.99
    ī
    2.96
    ´
    2.86
    Ħ
    2.83
    °
    2.81
    ĥ
    2.80
    ·
    2.78
    Activations Density 0.149%

    No Known Activations