© 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 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. 11194
    Prev
    Next
    INDEX
    Explanations

    references to online platforms and technology

    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
    47
    +0.18
    1.0%
    507
    +0.13
    0.7%
    92
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    92
    +0.18
    0.08
    47
    +0.13
    0.12
    41
    +0.12
    0.10
    Negative Logits
    Ŀ
    -1.96
    »
    -1.84
    ophagus
    -1.83
    ¬
    -1.77
    ķ
    -1.73
    ©
    -1.67
    Ĺ
    -1.63
    ²
    -1.63
    Ľ
    -1.61
    ĻĤ
    -1.58
    POSITIVE LOGITS
    lite
    1.53
    esque
    1.52
    sev
    1.45
    usiness
    1.41
    etry
    1.40
     Pradesh
    1.38
    ®
    1.34
     nick
    1.33
     grounds
    1.33
     Matter
    1.32
    Activations Density 2.163%

    No Known Activations