© 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. 4-RES-SM
    11. 12065
    Prev
    Next
    INDEX
    Explanations

    references to technology-related concepts

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    397
    +0.21
    1.3%
    78
    +0.20
    1.3%
    21
    +0.14
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    397
    +0.21
    0.14
    352
    +0.20
    0.10
    9
    +0.14
    0.10
    Negative Logits
    ĥ½
    -2.13
    ĻĤ
    -2.04
    ¡
    -1.74
    ·¸
    -1.67
    ł
    -1.67
    Ļª
    -1.65
    £
    -1.58
    ¿
    -1.58
    ©
    -1.54
    ķ
    -1.53
    POSITIVE LOGITS
    ...?"
    1.57
    ”?
    1.47
    "?
    1.42
    '?
    1.39
     footballers
    1.38
    ?”
    1.36
    ?’
    1.36
    ?'
    1.31
    âĢ¦”
    1.30
    ?!
    1.29
    Activations Density 3.078%

    No Known Activations