© 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. 28660
    Prev
    Next
    INDEX
    Explanations

    numerical patterns and sequences

    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
    369
    +0.19
    1.0%
    396
    +0.14
    0.8%
    292
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    307
    +0.19
    0.04
    82
    +0.14
    0.03
    30
    +0.14
    0.03
    Negative Logits
    ever
    -1.75
     envy
    -1.62
    lectual
    -1.56
    atement
    -1.55
     unity
    -1.50
     warfare
    -1.50
     interference
    -1.47
     infinity
    -1.43
     rich
    -1.40
     repetition
    -1.39
    POSITIVE LOGITS
    ĥ½
    2.17
    ĺ
    2.15
    ³
    2.11
    į
    2.04
    Ľ
    1.96
    Ł
    1.73
    £
    1.70
    ĻĤ
    1.68
    00
    1.66
    ł
    1.64
    Activations Density 0.185%

    No Known Activations