© 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. 28696
    Prev
    Next
    INDEX
    Explanations

    programming functions and their associated parameters

    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
    +0.14
    0.8%
    277
    +0.13
    0.7%
    287
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    287
    +0.14
    0.16
    243
    +0.13
    0.14
    282
    +0.13
    0.09
    Negative Logits
     Critical
    -1.41
     participant
    -1.33
     vehicle
    -1.31
     alike
    -1.29
     Deb
    -1.28
     instance
    -1.28
    moderate
    -1.27
    ress
    -1.25
    ITION
    -1.25
     offender
    -1.24
    POSITIVE LOGITS
    '));
    1.51
    ĸ´
    1.47
    ¿½
    1.41
    âĢħ
    1.40
    iscus
    1.40
    Ł
    1.36
    Ĺ
    1.34
     £
    1.31
    '),
    1.31
    '))
    1.28
    Activations Density 4.593%

    No Known Activations