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

    Neuronpedia

    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. 12375
    Prev
    Next
    INDEX
    Explanations

    HTML tags and related markup language elements

    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
    271
    +0.18
    1.0%
    12
    +0.11
    0.6%
    459
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    459
    +0.18
    0.13
    16
    +0.11
    0.07
    123
    +0.10
    0.12
    Negative Logits
    »¿
    -1.65
    ¿½
    -1.53
    ±
    -1.50
    ´
    -1.47
    ¾
    -1.45
    Ļ
    -1.43
    ľ
    -1.41
     aside
    -1.40
    Ģ
    -1.39
    ·¸
    -1.39
    POSITIVE LOGITS
    cible
    1.59
    )](#
    1.45
    upon
    1.45
    rew
    1.45
    following
    1.44
     Spacewatch
    1.40
    iginally
    1.36
     existed
    1.34
     range
    1.33
    roc
    1.31
    Activations Density 4.547%

    No Known Activations