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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11369
    Prev
    Next
    INDEX
    Explanations

    details related to events and promotional offers

    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
    156
    +0.33
    2.0%
    302
    +0.15
    0.9%
    76
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    509
    +0.33
    0.10
    57
    +0.15
    0.09
    430
    +0.14
    0.06
    Negative Logits
    "}](#
    -1.76
    ãĥ³ãĥĪ
    -1.57
    orent
    -1.55
    openh
    -1.54
    ils
    -1.53
    ãĤĩ
    -1.44
    еÑģÑĤ
    -1.43
    óg
    -1.40
    оÑģ
    -1.38
    ilot
    -1.37
    POSITIVE LOGITS
    ĻĤ
    1.67
    emat
    1.59
    IJ
    1.56
    ABILITY
    1.46
    ĩ
    1.42
    reviewed
    1.42
    ĥ½
    1.38
    ľĵ
    1.36
     opportunities
    1.33
    Ļª
    1.27
    Activations Density 4.806%

    No Known Activations