© 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. 11327
    Prev
    Next
    INDEX
    Explanations

    technical terms and instructions related to software or programming languages

    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
    +0.16
    0.9%
    130
    +0.15
    0.9%
    507
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    130
    +0.16
    0.18
    384
    +0.15
    0.08
    176
    +0.12
    0.14
    Negative Logits
    ¹
    -3.25
    Ĭ
    -3.16
    Īĺ
    -3.05
    µ
    -2.88
    ª
    -2.87
    «
    -2.87
    ¦
    -2.84
    ¬
    -2.83
    ¡
    -2.76
    ¸
    -2.75
    POSITIVE LOGITS
    arching
    1.83
    )$)
    1.63
    hend
    1.47
    '))
    1.46
     Redist
    1.46
    contrib
    1.45
    theorem
    1.43
    "))
    1.40
    "){
    1.39
    framework
    1.35
    Activations Density 4.758%

    No Known Activations